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

    Neuronpedia

    INDEX
    Explanations

    woff

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <!--
    -0.07
     Cách
    -0.07
     lesbians
    -0.07
    $d
    -0.07
     setAddress
    -0.06
     resizeMode
    -0.06
    ือด
    -0.06
     станет
    -0.06
    localized
    -0.06
    Payload
    -0.06
    POSITIVE LOGITS
    학
    0.08
    дах
    0.07
     동
    0.07
     eyeb
    0.06
    ち
    0.06
     philosophical
    0.06
     utilizes
    0.06
     desenv
    0.06
     Personal
    0.06
     eb
    0.06
    Act Density 0.001%

    No Known Activations