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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    참고
    -0.61
    rouvez
    -0.61
    AnchorStyles
    -0.60
    HtmlAttribute
    -0.60
    SequentialGroup
    -0.52
    jmniej
    -0.52
     Référence
    -0.52
    новниш
    -0.51
    خصة
    -0.51
     elseif
    -0.49
    POSITIVE LOGITS
     of
    0.59
     apprécié
    0.52
     about
    0.52
     laiko
    0.51
    styleType
    0.50
     feroit
    0.50
    parer
    0.49
     ainfi
    0.49
     Bearer
    0.49
     faker
    0.49
    Act Density 0.001%

    No Known Activations