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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mqtt
    -0.08
    ctp
    -0.08
        ↵    ↵    ↵
    -0.07
    enever
    -0.07
    nw
    -0.07
    english
    -0.07
     Ebony
    -0.07
    [ix
    -0.07
    den
    -0.07
    нный
    -0.07
    POSITIVE LOGITS
    .social
    0.08
    @store
    0.07
     cm
    0.07
     truncated
    0.07
    =random
    0.07
     lur
    0.07
    aron
    0.06
    下載
    0.06
    ⥂
    0.06
    🄲
    0.06
    Act Density 0.001%

    No Known Activations