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

    Neuronpedia

    INDEX
    Explanations

    specific situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anten
    0.36
    ”
    0.36
    吿
    0.35
     थोड़ा
    0.34
    s
    0.34
    ameras
    0.34
     ஏற்கனவே
    0.34
    ാ
    0.34
    ely
    0.33
     হয়তো
    0.33
    POSITIVE LOGITS
     alteraciones
    0.45
     मूवी
    0.42
     हेतु
    0.39
    拵
    0.38
     alteration
    0.38
    རྒྱ
    0.37
    膂
    0.36
     dependability
    0.36
     renferme
    0.36
    멎
    0.36
    Act Density 2.097%

    No Known Activations