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

    Neuronpedia

    INDEX
    Explanations

    keyword suggestions and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᴺ
    0.44
    KeyState
    0.42
    ChooseCharacter
    0.42
    gateTime
    0.42
    বারের
    0.41
     enseign
    0.40
    ajā
    0.40
    clementine
    0.40
     الإنترنت
    0.39
     ненави
    0.39
    POSITIVE LOGITS
     Working
    0.54
     The
    0.50
    商品は
    0.49
     Cumulative
    0.47
     Hydraulic
    0.46
    ைச்
    0.46
     Functional
    0.46
    匀
    0.45
     brackets
    0.45
     leave
    0.44
    Act Density 0.000%

    No Known Activations