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

    Neuronpedia

    INDEX
    Explanations

    damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Processing
    -0.06
    -la
    -0.06
     Km
    -0.06
    문
    -0.06
    ReturnValue
    -0.06
    Hot
    -0.06
    _ar
    -0.06
    سبب
    -0.06
    Sphere
    -0.06
    pirit
    -0.06
    POSITIVE LOGITS
    ),↵
    0.06
    plers
    0.06
    803
    0.06
    (size
    0.06
    LEGRO
    0.06
    ssi
    0.06
     echoed
    0.06
     avoidance
    0.06
    olet
    0.06
    /plain
    0.06
    Act Density 0.052%

    No Known Activations