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

    Neuronpedia

    INDEX
    Explanations

    auxiliary/connecting words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    璃
    -0.07
     rng
    -0.07
     Overse
    -0.07
     Sext
    -0.06
    Dia
    -0.06
    rack
    -0.06
    TN
    -0.06
    _system
    -0.06
    [d
    -0.06
    -wise
    -0.06
    POSITIVE LOGITS
    监听页面
    0.07
     #{@
    0.07
    μος
    0.06
     TI
    0.06
     Shall
    0.06
     Interestingly
    0.06
     DataRow
    0.06
     consolid
    0.06
    ,readonly
    0.06
     olabilir
    0.06
    Act Density 0.056%

    No Known Activations