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

    Neuronpedia

    INDEX
    Explanations

    good explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вторых
    0.66
     угле
    0.65
     enanti
    0.63
    isterschaft
    0.63
    कलन
    0.61
    ֙
    0.60
     平
    0.59
    aminan
    0.59
    힣
    0.59
    чы
    0.58
    POSITIVE LOGITS
    The
    0.61
    tau
    0.55
     The
    0.54
    There
    0.51
    Shr
    0.50
    Tau
    0.50
    Ratio
    0.50
     Dif
    0.49
     Salam
    0.49
    વાસ
    0.49
    Act Density 0.000%

    No Known Activations