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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    queda
    -0.06
     nikdo
    -0.06
    ;border
    -0.06
    <main
    -0.06
     dipped
    -0.06
    uilt
    -0.06
     thu
    -0.06
    .AppSettings
    -0.06
    бі
    -0.06
     humiliating
    -0.06
    POSITIVE LOGITS
    $s
    0.08
    516
    0.07
     Examiner
    0.07
    Retention
    0.06
     Thom
    0.06
     연구
    0.06
     pigs
    0.06
     Stephanie
    0.06
     quem
    0.06
    valuator
    0.06
    Act Density 0.000%

    No Known Activations