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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of artistic or creative expression

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

    Lists of things, often with a description

    np_acts-logits-general · gemini-2.0-flash

    ending list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infatti
    -0.60
    complexType
    -0.56
    ParallelGroup
    -0.54
     namelijk
    -0.54
    parsedMessage
    -0.53
     Infatti
    -0.51
     aceea
    -0.49
     bowiem
    -0.48
     polega
    -0.48
    styleType
    -0.45
    POSITIVE LOGITS
     etc
    0.82
    etc
    0.73
     Etc
    0.58
    Etc
    0.57
     semuanya
    0.54
     these
    0.54
     These
    0.54
    这些
    0.50
    等等
    0.50
     Basically
    0.50
    Act Density 0.691%

    No Known Activations