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

    Neuronpedia

    INDEX
    Explanations

    escape

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voice
    -0.07
     heavyweight
    -0.06
     dots
    -0.06
     fans
    -0.06
    .Tx
    -0.06
     wireless
    -0.06
     ワ
    -0.06
     arithmetic
    -0.06
    _tp
    -0.06
     ذ
    -0.06
    POSITIVE LOGITS
     CrossRef
    0.07
    düğ
    0.06
     गए
    0.06
    živ
    0.06
    lí
    0.06
    ]);
↵
↵
    0.06
    Cette
    0.06
     urlparse
    0.06
     estos
    0.06
     reversal
    0.06
    Act Density 0.011%

    No Known Activations