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

    Neuronpedia

    INDEX
    Explanations

    non-english texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     to
    -0.09
     on
    -0.08
     in
    -0.08
     in
    -0.08
     Stanley
    -0.07
    -to
    -0.07
     ON
    -0.07
     TO
    -0.07
     In
    -0.07
     약
    -0.07
    POSITIVE LOGITS
    xCF
    0.08
    .createTextNode
    0.07
     des
    0.07
    asterxml
    0.07
     зна
    0.07
     των
    0.07
     �
    0.07
     će
    0.07
     ενός
    0.07
     eines
    0.06
    Act Density 0.077%

    No Known Activations