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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     هل
    -0.07
    ref
    -0.07
     prized
    -0.06
    COVER
    -0.06
     REGARD
    -0.06
     heyec
    -0.06
    /V
    -0.06
    374
    -0.06
    (pwd
    -0.06
    USE
    -0.06
    POSITIVE LOGITS
     lung
    0.07
    Las
    0.07
     ilç
    0.06
    智能
    0.06
    lung
    0.06
     �
    0.06
    _free
    0.06
    报
    0.06
    Input
    0.06
    pixel
    0.06
    Act Density 0.061%

    No Known Activations