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

    Neuronpedia

    INDEX
    Explanations

    casual suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Educ
    -0.07
    acionales
    -0.07
     RESPONS
    -0.07
    Dto
    -0.07
     ano
    -0.07
     fm
    -0.07
     národ
    -0.07
    ุญาต
    -0.06
    .cr
    -0.06
    Learn
    -0.06
    POSITIVE LOGITS
     gunfire
    0.06
     likelihood
    0.06
    metrics
    0.06
    (images
    0.06
     сви
    0.06
     dissolved
    0.06
    поч
    0.06
    _clear
    0.06
    bolt
    0.06
    Fields
    0.06
    Act Density 0.007%

    No Known Activations