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

    Neuronpedia

    INDEX
    Explanations

    basic to specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    χω
    0.43
    कायदा
    0.43
     switch
    0.41
     sheer
    0.39
     सार्व
    0.39
     ampli
    0.39
     aparece
    0.38
     έχ
    0.38
    ᅯ
    0.38
    鳗
    0.38
    POSITIVE LOGITS
    Async
    0.37
     Pflicht
    0.37
    影像
    0.36
    resin
    0.36
    ft
    0.36
    mmm
    0.36
     descoper
    0.35
    important
    0.35
    sparse
    0.35
    concern
    0.35
    Act Density 0.000%

    No Known Activations