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

    Neuronpedia

    INDEX
    Explanations

    and or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    200
    -0.07
     liberty
    -0.06
    195
    -0.06
     ucwords
    -0.06
    .'↵
    -0.06
     Citation
    -0.06
    lessons
    -0.06
    110
    -0.06
     있다
    -0.06
    351
    -0.06
    POSITIVE LOGITS
    ogonal
    0.07
    	Type
    0.07
     अश
    0.06
    	flags
    0.06
    .FontStyle
    0.06
    nota
    0.06
    Раз
    0.06
    _IMAGES
    0.06
    策
    0.06
    	Read
    0.06
    Act Density 0.166%

    No Known Activations