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

    Neuronpedia

    INDEX
    Explanations

    '`s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prothorace
    0.05
     dictated
    0.04
    rjust
    0.04
    ianSpace
    0.04
     wreak
    0.04
     approachable
    0.04
     markedly
    0.04
     lineColorSpace
    0.04
     aise
    0.04
     scheming
    0.04
    POSITIVE LOGITS
     of
    0.04
     हुए
    0.04
    ו
    0.03
    ungen
    0.03
     کردن
    0.03
     বা
    0.03
    uk
    0.03
    os
    0.03
    ib
    0.03
    べき
    0.03
    Act Density 0.002%

    No Known Activations