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

    Neuronpedia

    INDEX
    Explanations

    political opponents, etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रकट
    0.47
    𝔰
    0.45
     വീ
    0.45
    之路
    0.45
    Locations
    0.44
     লম্বা
    0.43
    Ầ
    0.42
    多个
    0.42
     মেঝে
    0.41
    penas
    0.41
    POSITIVE LOGITS
     simpat
    0.43
     judicious
    0.42
    argsort
    0.42
    чить
    0.42
     поможет
    0.42
     foolproof
    0.41
     conducive
    0.39
     of
    0.39
    untar
    0.39
     ():
    0.39
    Act Density 0.005%

    No Known Activations