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

    Neuronpedia

    INDEX
    Explanations

    Code-related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unky
    -0.06
     veteran
    -0.06
    spe
    -0.06
     Alger
    -0.06
    经过
    -0.06
     unfavor
    -0.06
    Amy
    -0.06
    ValidationError
    -0.06
    しても
    -0.06
    kses
    -0.06
    POSITIVE LOGITS
     кор
    0.07
    681
    0.07
    _codes
    0.07
    764
    0.07
    _approved
    0.07
    】↵↵
    0.07
    oulos
    0.06
    .frequency
    0.06
     tük
    0.06
    customerId
    0.06
    Act Density 0.093%

    No Known Activations