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

    Neuronpedia

    INDEX
    Explanations

    oris

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Justice
    -0.07
     я
    -0.07
    ха
    -0.07
    （
    -0.07
     arrogant
    -0.06
    (string
    -0.06
     ад
    -0.06
     ним
    -0.06
    _known
    -0.06
    .Texture
    -0.06
    POSITIVE LOGITS
     ört
    0.07
     Бор
    0.07
    borg
    0.07
    agr
    0.07
     overlooked
    0.06
    .columnHeader
    0.06
    definitions
    0.06
    reason
    0.06
    827
    0.06
    ＼
    0.06
    Act Density 0.006%

    No Known Activations