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

    Neuronpedia

    INDEX
    Explanations

    equivalence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشين
    -1.13
     Theſe
    -1.10
     Efq
    -1.06
    GEBURTSDATUM
    -1.01
    oredCriteria
    -0.99
     Anſ
    -0.96
    تقاوى
    -0.96
    Geplaatst
    -0.95
     Shakspeare
    -0.95
    -0.94
    POSITIVE LOGITS
    s
    0.88
    ly
    0.56
     due
    0.53
     and
    0.52
    y
    0.52
     dis
    0.49
     time
    0.49
    es
    0.49
    ی
    0.49
    en
    0.48
    Act Density 0.070%

    No Known Activations