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

    Neuronpedia

    INDEX
    Explanations

    iter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    URLOPT
    -0.08
     отношения
    -0.07
    ADV
    -0.07
    omics
    -0.07
     Warriors
    -0.07
     Lung
    -0.06
     दल
    -0.06
    trinsic
    -0.06
     QName
    -0.06
    vore
    -0.06
    POSITIVE LOGITS
     heater
    0.07
    ?)↵↵
    0.07
    194
    0.06
    を使
    0.06
    677
    0.06
     Orlando
    0.06
    .*/↵
    0.06
     unexpected
    0.06
    _)↵
    0.06
     charges
    0.06
    Act Density 0.000%

    No Known Activations