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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “When
    -0.06
     recursively
    -0.06
    minecraft
    -0.06
    _nc
    -0.06
    	light
    -0.06
     direkt
    -0.06
     kayak
    -0.06
    /string
    -0.06
    建议
    -0.06
    astically
    -0.06
    POSITIVE LOGITS
    .fromString
    0.07
    ofday
    0.07
    ocene
    0.06
    іт
    0.06
    se
    0.06
     JNIEnv
    0.06
    pan
    0.06
     öyle
    0.06
    [slot
    0.06
     họ
    0.06
    Act Density 0.117%

    No Known Activations