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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    coordinate
    -0.07
     coordinated
    -0.07
    _orient
    -0.07
     wording
    -0.07
    stations
    -0.07
    ulti
    -0.07
    ığ
    -0.07
    яз
    -0.07
     birinci
    -0.06
    ableOpacity
    -0.06
    POSITIVE LOGITS
     congratulate
    0.06
     Grants
    0.06
     plum
    0.06
    (TypeError
    0.06
    =:
    0.06
     conservative
    0.06
     UNION
    0.06
    ojis
    0.06
    .ml
    0.06
     наш
    0.06
    Act Density 0.032%

    No Known Activations