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

    Neuronpedia

    INDEX
    Explanations

    providing factual information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    1.00
     be
    0.84
    ä
    0.75
    \
    0.64
    ö
    0.63
     but
    0.63
    _{
    0.62
    с
    0.62
     in
    0.61
     so
    0.58
    POSITIVE LOGITS
    i
    0.71
    ي
    0.61
    헹
    0.60
     exemplaires
    0.59
     Consultado
    0.59
     rameaux
    0.59
    r
    0.59
     conclu
    0.58
     anciens
    0.58
     envoyer
    0.58
    Act Density 5.272%

    No Known Activations