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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OXIDES
    0.31
     CHCl
    0.31
    𒋼
    0.31
     Elektrokhimiya
    0.29
    ᕇ
    0.29
     Elovl
    0.29
    存档备份
    0.29
     Pogis
    0.29
     fibrils
    0.29
    𒀸
    0.29
    POSITIVE LOGITS
    //
    0.63
    /*
    0.57
    if
    0.53
    ↵
    0.45
    #
    0.44
    try
    0.44
    /**
    0.43
    ///
    0.42
    const
    0.41
    int
    0.40
    Act Density 0.233%

    No Known Activations