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

    Neuronpedia

    INDEX
    Explanations

    spending

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     produk
    0.66
     produktu
    0.64
     kahi
    0.61
     craters
    0.59
     cerebro
    0.59
    ismuth
    0.59
     beanie
    0.58
     სპეცი
    0.58
    roke
    0.57
     खेला
    0.57
    POSITIVE LOGITS
    Initi
    0.57
    Batman
    0.56
    🏢
    0.55
     mature
    0.54
     પ્રાપ્ત
    0.52
     मंजूर
    0.51
    aptan
    0.51
    zeigen
    0.51
     Exodus
    0.51
    そもそも
    0.51
    Act Density 0.000%

    No Known Activations