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
     federation
    -0.07
    (it
    -0.06
     MO
    -0.06
    (latitude
    -0.06
    St
    -0.06
    rání
    -0.06
     Asp
    -0.06
     愛
    -0.06
     vive
    -0.06
    Constraint
    -0.06
    POSITIVE LOGITS
    .boolean
    0.07
     selfish
    0.06
    .nextDouble
    0.06
     osob
    0.06
    dır
    0.06
    _compute
    0.06
    udson
    0.06
    _online
    0.06
     Caval
    0.06
     Cambridge
    0.06
    Act Density 0.002%

    No Known Activations