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

    Neuronpedia

    INDEX
    Explanations

    repeated characters within words

    oai_token-act-pair · gemini-2.0-flash

    Probability and letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.79
    </caption>
    -0.70
    gway
    -0.68
    AutoresizingMask
    -0.68
     MonoBehaviour
    -0.66
    )"),
    -0.65
     ]]
    -0.65
    )");
    -0.64
    '%(
    -0.63
     kaynağından
    -0.62
    POSITIVE LOGITS
    StructEnd
    0.63
    +#+#
    0.57
     Kaka
    0.55
     Babcock
    0.55
    wechsel
    0.54
    ことです
    0.52
    djangoproject
    0.52
     tertarik
    0.52
     représ
    0.51
     koko
    0.51
    Act Density 2.471%

    No Known Activations