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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    speech
    -0.07
     Decoration
    -0.07
     marry
    -0.07
    Ka
    -0.06
     Templ
    -0.06
     Enumerable
    -0.06
     runner
    -0.06
    upiter
    -0.06
    едь
    -0.06
     supermarket
    -0.06
    POSITIVE LOGITS
     kleine
    0.06
    noinspection
    0.06
    」
    0.06
    _proj
    0.06
    //!
    0.06
    Artifact
    0.06
     pca
    0.06
     Kathleen
    0.06
     tarım
    0.06
     scratch
    0.06
    Act Density 0.008%

    No Known Activations