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

    Neuronpedia

    INDEX
    Explanations

    positive assessments and evaluations

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

    "good" or similar positive sentiment

    np_acts-logits-general · gemini-2.0-flash

    good followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Correct
    -0.57
    InjectAttribute
    -0.57
     perfect
    -0.56
    Perfect
    -0.55
     getRule
    -0.54
     Perfect
    -0.53
    perfect
    -0.53
     perfeito
    -0.52
    ιώ
    -0.52
    PERFECT
    -0.52
    POSITIVE LOGITS
    DoubleQuotes
    0.83
     value
    0.83
     deal
    0.78
     quality
    0.76
    ulously
    0.75
    SourceChecksum
    0.72
    koper
    0.70
     deals
    0.70
     defaultstate
    0.70
    دانشنامهٔ
    0.70
    Act Density 0.140%

    No Known Activations