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

    Neuronpedia

    INDEX
    Explanations

    Memberships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ฟร
    -0.07
     Lange
    -0.06
    ()")↵
    -0.06
     backs
    -0.06
    dit
    -0.06
    ござ
    -0.06
    ullivan
    -0.06
    IU
    -0.06
    게임
    -0.06
    nicos
    -0.06
    POSITIVE LOGITS
    _patches
    0.07
    _goto
    0.07
    基础
    0.07
     caz
    0.06
     aug
    0.06
    klass
    0.06
     photograph
    0.06
     prepare
    0.06
    InputElement
    0.06
     vox
    0.06
    Act Density 0.025%

    No Known Activations