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

    Neuronpedia

    INDEX
    Explanations

    news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pace
    -0.08
     enclosure
    -0.07
    ury
    -0.07
     Faith
    -0.06
     exchanges
    -0.06
     Above
    -0.06
     Hd
    -0.06
    .phase
    -0.06
    FRING
    -0.06
    ller
    -0.06
    POSITIVE LOGITS
     broadly
    0.07
    _deg
    0.06
    DOCKER
    0.06
    .FromResult
    0.06
    861
    0.06
    できます
    0.06
    .propTypes
    0.06
     بم
    0.06
    0.06
    831
    0.06
    Act Density 0.001%

    No Known Activations