Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    discussions about errors and troubleshooting in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text snippets from technical support Q&As

    np_acts-logits-general · gemini-2.0-flash

    statement followed by question or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.79
    InjectAttribute
    -0.78
     '\\;'
    -0.71
    ValueGeneration
    -0.69
     NavController
    -0.68
    parsedMessage
    -0.67
     createSprite
    -0.67
    OGND
    -0.67
     Commencez
    -0.64
    EndContext
    -0.63
    POSITIVE LOGITS
     when
    0.69
     seharusnya
    0.66
     Apparently
    0.64
     When
    0.63
     strangely
    0.61
    Doh
    0.58
     apparently
    0.58
    when
    0.58
    When
    0.58
    Shouldn
    0.57
    Act Density 0.603%

    No Known Activations