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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     awakened
    -0.07
    #c
    -0.07
    cel
    -0.06
    は
    -0.06
    _estimators
    -0.06
    .bam
    -0.06
     Pressure
    -0.06
    ('_
    -0.06
     когда
    -0.06
    ereotype
    -0.06
    POSITIVE LOGITS
     Unsure
    0.07
    Aus
    0.06
    .toJSON
    0.06
    .getStyle
    0.06
    (json
    0.06
     cork
    0.06
     기간
    0.05
     extraordinary
    0.05
    柏
    0.05
    .execute
    0.05
    Act Density 0.049%

    No Known Activations