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
    铁路
    -0.07
     گذشته
    -0.07
     parenthesis
    -0.07
     -*-
    -0.07
    collapsed
    -0.06
    .COM
    -0.06
     хвор
    -0.06
    .CheckedChanged
    -0.06
     Values
    -0.06
    ListBox
    -0.06
    POSITIVE LOGITS
     insecure
    0.07
    _EM
    0.06
    entrant
    0.06
    .Secret
    0.06
    */
    0.06
    -task
    0.06
    τομα
    0.06
     manually
    0.06
    sek
    0.06
    reflection
    0.06
    Act Density 0.000%

    No Known Activations