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

    Neuronpedia

    INDEX
    Explanations

    business offers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -1.00
     a
    -0.78
     us
    -0.71
     their
    -0.71
     its
    -0.69
     your
    -0.67
     an
    -0.66
     it
    -0.65
     his
    -0.65
     another
    -0.63
    POSITIVE LOGITS
     of
    0.91
     löyty
    0.54
     itſelf
    0.54
     pleaſure
    0.54
     italienne
    0.53
    المشاركات
    0.52
    able
    0.50
     extérieures
    0.49
     âgées
    0.49
    ment
    0.49
    Act Density 0.113%

    No Known Activations