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

    Neuronpedia

    INDEX
    Explanations

    tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    話
    -0.07
     reproductive
    -0.07
     AHL
    -0.07
     شناخته
    -0.07
    사는
    -0.07
    'B
    -0.06
     založ
    -0.06
    .findIndex
    -0.06
    /Base
    -0.06
    _inp
    -0.06
    POSITIVE LOGITS
    (rr
    0.07
     pairwise
    0.07
     sembl
    0.06
     karş
    0.06
    Su
    0.06
     sat
    0.06
    .SUCCESS
    0.06
     exhilar
    0.06
    	rows
    0.06
     chod
    0.06
    Act Density 0.021%

    No Known Activations