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

    Neuronpedia

    INDEX
    Explanations

    urls with identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.81
     ہل
    0.80
     eixo
    0.80
    なん
    0.79
     certes
    0.77
    ற்ச
    0.77
     festa
    0.77
     ㅇ
    0.75
     هاکي
    0.75
    0.74
    POSITIVE LOGITS
    urrent
    0.59
     afflict
    0.56
     შემდეგ
    0.56
    ผิด
    0.56
     variance
    0.55
    ลาย
    0.55
    achi
    0.55
     Visualization
    0.54
    اتي
    0.54
    错误的
    0.53
    Act Density 0.044%

    No Known Activations