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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	cin
    -0.07
    _valid
    -0.07
     fulfill
    -0.07
    .compile
    -0.07
     store
    -0.06
    ũ
    -0.06
    _validation
    -0.06
    stitute
    -0.06
     lit
    -0.06
    /Input
    -0.06
    POSITIVE LOGITS
     кноп
    0.07
     SKU
    0.07
    棤
    0.07
    rating
    0.07
     blanco
    0.06
    orris
    0.06
     patter
    0.06
     באר
    0.06
    ACHINE
    0.06
    .discount
    0.06
    Act Density 0.002%

    No Known Activations