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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     社
    -0.07
     нік
    -0.07
    ORITY
    -0.07
     Khu
    -0.06
     rady
    -0.06
     Profile
    -0.06
    [train
    -0.06
    .enc
    -0.06
    (grid
    -0.06
     داو
    -0.06
    POSITIVE LOGITS
    ỷ
    0.06
     IActionResult
    0.06
    Renderer
    0.06
     guerr
    0.06
    :left
    0.06
    utches
    0.06
     charged
    0.06
    inson
    0.06
    ектив
    0.06
    ...";↵
    0.06
    Act Density 0.192%

    No Known Activations