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

    Neuronpedia

    INDEX
    Explanations

    response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sod
    -0.06
     역
    -0.06
     yeter
    -0.06
    TeV
    -0.06
    ост
    -0.06
     MIPS
    -0.06
    glich
    -0.06
     आल
    -0.06
    nier
    -0.05
    략
    -0.05
    POSITIVE LOGITS
    _surface
    0.07
    ::$
    0.07
     olacağ
    0.07
     Citation
    0.07
     doub
    0.07
    merged
    0.06
    -http
    0.06
    しま
    0.06
     <
    0.06
     HAL
    0.06
    Act Density 0.008%

    No Known Activations