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

    Neuronpedia

    INDEX
    Explanations

    converting bases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collectively
    -0.08
    。这
    -0.08
     sammeln
    -0.08
     gesammelt
    -0.07
     wrists
    -0.07
     ery
    -0.07
     sick
    -0.07
    etted
    -0.07
     bibli
    -0.07
    来自
    -0.07
    POSITIVE LOGITS
    Descending
    0.10
    descending
    0.09
    Quota
    0.09
    ancestor
    0.08
     descending
    0.08
     tono
    0.08
    _desc
    0.08
    Substring
    0.08
    ಕ್ರಮ
    0.08
    Eliminar
    0.08
    Act Density 0.023%

    No Known Activations