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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atal
    -0.06
    ulta
    -0.06
    Republic
    -0.06
     "");
↵
    -0.06
    صول
    -0.06
     torchvision
    -0.06
    REAK
    -0.06
    دود
    -0.06
    -launch
    -0.06
    ahrungen
    -0.06
    POSITIVE LOGITS
     over
    0.11
     Over
    0.09
     zeros
    0.07
    Under
    0.07
     under
    0.07
     Under
    0.07
     OVER
    0.07
    _vec
    0.07
     Insert
    0.07
     lowercase
    0.07
    Act Density 0.011%

    No Known Activations