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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ал
    -0.07
    ….↵↵
    -0.07
    倍
    -0.07
    obraz
    -0.06
     Аб
    -0.06
     rendre
    -0.06
    UBLE
    -0.06
    、『
    -0.06
    $L
    -0.06
    ADB
    -0.06
    POSITIVE LOGITS
    .son
    0.07
     TO
    0.07
    persons
    0.07
    egrated
    0.07
     To
    0.07
    .onCreate
    0.07
    ्मक
    0.07
     sở
    0.07
     should
    0.06
    loys
    0.06
    Act Density 0.006%

    No Known Activations