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

    Neuronpedia

    INDEX
    Explanations

    isn't it?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是指
    0.79
    +...+
    0.79
     osp
    0.77
    いたら
    0.77
     해당
    0.76
     unsigned
    0.76
     take
    0.75
     substantially
    0.75
    וק
    0.75
     করিলাম
    0.75
    POSITIVE LOGITS
     eloquent
    0.76
    Agree
    0.76
    irrit
    0.75
     Alltag
    0.73
     हळ
    0.71
     unanim
    0.71
    課
    0.70
    नुसार
    0.70
    IZED
    0.70
     costruire
    0.69
    Act Density 0.018%

    No Known Activations