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

    Neuronpedia

    INDEX
    Explanations

    team at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    সর্ব
    0.73
     försö
    0.72
    度が
    0.71
     svak
    0.69
    вичайно
    0.68
    置
    0.66
    ทำให้
    0.65
     segregation
    0.65
     samband
    0.63
    োজিত
    0.63
    POSITIVE LOGITS
     include
    0.94
     includes
    0.93
     down
    0.91
     turn
    0.84
     inches
    0.83
     included
    0.80
     go
    0.78
     are
    0.77
     downs
    0.75
    turn
    0.73
    Act Density 0.005%

    No Known Activations