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

    Neuronpedia

    INDEX
    Explanations

    mask

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ruise
    -0.07
    atown
    -0.07
     [
    -0.07
     nền
    -0.07
    yling
    -0.06
    .maxLength
    -0.06
    [
    -0.06
     ([
    -0.06
     occupants
    -0.06
    ียด
    -0.06
    POSITIVE LOGITS
    _blocked
    0.06
     Möglichkeit
    0.06
    utenant
    0.06
    !<
    0.06
     nimi
    0.06
    ‌خ
    0.06
    生き
    0.06
    _PWM
    0.06
     concaten
    0.06
     شناخته
    0.06
    Act Density 0.000%

    No Known Activations