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

    Neuronpedia

    INDEX
    Explanations

    guid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Test
    -0.07
    时刻
    -0.07
    ="_
    -0.07
    zar
    -0.07
     multiplied
    -0.07
    𬩽
    -0.06
    潢
    -0.06
    丙
    -0.06
     Cristina
    -0.06
    事业
    -0.06
    POSITIVE LOGITS
     Aus
    0.07
    _md
    0.07
    �
    0.07
    (emp
    0.07
    _mut
    0.07
    ,DB
    0.07
    $results
    0.07
    慕
    0.07
    sı
    0.07
    .par
    0.06
    Act Density 0.003%

    No Known Activations