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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sélection
    -0.07
     февра
    -0.07
     limited
    -0.07
     Bit
    -0.07
     formally
    -0.07
     Coordinate
    -0.07
     fw
    -0.06
     IPv
    -0.06
     go
    -0.06
     floatValue
    -0.06
    POSITIVE LOGITS
    雪
    0.06
    cth
    0.06
    acted
    0.06
     Medicaid
    0.06
    iker
    0.06
    annies
    0.06
    ンチ
    0.06
    쉬
    0.06
    artment
    0.06
    ле
    0.06
    Act Density 0.000%

    No Known Activations