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

    Neuronpedia

    INDEX
    Explanations

    programming syntax characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _logo
    -0.08
    👓
    -0.08
    뉴스
    -0.08
    (Runtime
    -0.07
    .Des
    -0.07
    �
    -0.07
    _Position
    -0.07
    -Disposition
    -0.07
     postseason
    -0.07
     BTN
    -0.07
    POSITIVE LOGITS
     gauge
    0.08
    說明
    0.07
    structions
    0.07
    掺
    0.07
     dB
    0.07
     incl
    0.07
     ب
    0.07
    截
    0.07
    ऋ
    0.06
    TZ
    0.06
    Act Density 0.007%

    No Known Activations