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

    Neuronpedia

    INDEX
    Explanations

    free entrance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ​​
    0.94
     all
    0.87
     the
    0.83
     t
    0.79
     a
    0.77
    TP
    0.76
     ο
    0.74
    TRACK
    0.74
    และความ
    0.74
    NIH
    0.73
    POSITIVE LOGITS
    ism
    0.93
    rors
    0.89
     pewno
    0.88
    is
    0.88
    ‏:‏
    0.88
    ilable
    0.88
    ,【
    0.87
    ,(
    0.86
     vardır
    0.86
    ir
    0.85
    Act Density 0.644%

    No Known Activations