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

    Neuronpedia

    INDEX
    Explanations

    details related to visual elements and physical attributes in descriptions

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

    colour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -0.67
    TypedDataSet
    -0.67
     ſta
    -0.63
     eſſ
    -0.59
    ſelf
    -0.58
     juſ
    -0.58
     raiſ
    -0.57
     itſelf
    -0.56
     ſtand
    -0.55
     poffible
    -0.54
    POSITIVE LOGITS
    contentLoaded
    0.42
    ➋
    0.35
    createClass
    0.34
    édrale
    0.33
     cute
    0.31
     Believe
    0.31
     kutu
    0.31
     gotta
    0.30
     Another
    0.30
     Notice
    0.30
    Act Density 0.017%

    No Known Activations