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

    Neuronpedia

    INDEX
    Explanations

    your local emergency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Masai
    0.39
     Tx
    0.38
     either
    0.38
     Olimp
    0.38
    ினார்கள்
    0.37
    颞
    0.37
     توزيع
    0.37
     Newborn
    0.37
     Millennials
    0.37
    逄
    0.36
    POSITIVE LOGITS
     equivalent
    1.05
    equivalent
    0.94
     equivalents
    0.88
     Equivalent
    0.88
    Equivalent
    0.84
     equivalente
    0.79
     equival
    0.78
     equivalence
    0.72
    equival
    0.69
     Equival
    0.68
    Act Density 0.015%

    No Known Activations