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

    Neuronpedia

    INDEX
    Explanations

    attributes, qualities, or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tn
    0.53
     allgemeinen
    0.53
    Rn
    0.50
    zeugen
    0.49
    R
    0.49
     {\
    0.49
     හ
    0.49
     парла
    0.47
     ancienne
    0.47
    كان
    0.47
    POSITIVE LOGITS
    ness
    0.91
    पणे
    0.83
     بودن
    0.67
    NESS
    0.64
    .
    0.64
     ترین
    0.63
     ہونے
    0.62
     adjective
    0.61
     ness
    0.60
    さを
    0.59
    Act Density 0.418%

    No Known Activations