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

    Neuronpedia

    INDEX
    Explanations

    Error/constraint flagging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    films
    -0.08
    QQ
    -0.08
     Assets
    -0.07
     baths
    -0.07
    街
    -0.07
     arenas
    -0.07
    hoc
    -0.07
     horn
    -0.07
     erfahren
    -0.07
     vistas
    -0.07
    POSITIVE LOGITS
    上限
    0.07
     three
    0.07
    (TYPE
    0.07
    PLIC
    0.06
    (lo
    0.06
    	sprite
    0.06
    .itemId
    0.06
    imeType
    0.06
    Structure
    0.06
    뻣
    0.06
    Act Density 0.002%

    No Known Activations