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

    Neuronpedia

    INDEX
    Explanations

    Character descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SAMPLE
    -0.06
     LoginActivity
    -0.06
    Contains
    -0.06
    alace
    -0.05
    (Service
    -0.05
    (priority
    -0.05
    (Font
    -0.05
    PathParam
    -0.05
     Priority
    -0.05
     ноч
    -0.05
    POSITIVE LOGITS
    poster
    0.08
    tero
    0.07
    Did
    0.07
    URA
    0.07
    OWNER
    0.07
    licensed
    0.07
     OUR
    0.07
    ляет
    0.07
     mp
    0.06
     gram
    0.06
    Act Density 0.034%

    No Known Activations