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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     realization
    -0.07
    IDs
    -0.06
     Cros
    -0.06
     εμπ
    -0.06
     alıyor
    -0.06
    Walker
    -0.06
     Shea
    -0.06
    Senha
    -0.06
     Pearce
    -0.06
    важ
    -0.06
    POSITIVE LOGITS
    /")
    0.07
    _margin
    0.06
     (?)
    0.06
     wasm
    0.06
    disposing
    0.06
     배우
    0.06
    (low
    0.06
     ­
    0.06
     unveiled
    0.06
     iota
    0.06
    Act Density 0.087%

    No Known Activations