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

    Neuronpedia

    INDEX
    Explanations

    Perez Alvarez Lawrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ."
    -3.27
    ,"
    -3.25
     ergänzt
    -2.64
    ৢ
    -2.64
    ;"
    -2.63
     determinadas
    -2.59
    .,
    -2.56
     costs
    -2.53
     determinados
    -2.52
     finds
    -2.50
    POSITIVE LOGITS
    お店
    2.34
    流畅
    2.30
    s
    2.27
    Ꮠ
    2.25
     toer
    2.22
     otr
    2.19
    .
    2.16
    质感
    2.14
    Letra
    2.14
     usw
    2.14
    Act Density 0.009%

    No Known Activations