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

    Neuronpedia

    INDEX
    Explanations

    Examples `This` `You` `For`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    noon
    0.80
    ГЭ
    0.76
    ளாக்
    0.75
    imed
    0.73
    ங்கிணை
    0.72
     सहज
    0.72
     darn
    0.71
    odore
    0.71
    ਿਕ
    0.71
    不一樣
    0.69
    POSITIVE LOGITS
    ــــــــ
    0.87
    cdot
    0.84
     경우
    0.83
     hỏi
    0.83
    ــــ
    0.78
     Commit
    0.77
    См
    0.76
     প্রশংসা
    0.75
    frau
    0.75
    पृथ
    0.74
    Act Density 0.000%

    No Known Activations