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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (depth
    -0.07
     respawn
    -0.07
    nombre
    -0.07
     récup
    -0.07
    _PIN
    -0.07
    logen
    -0.07
    .ALL
    -0.07
     Pessoa
    -0.07
    /db
    -0.07
     Responsible
    -0.07
    POSITIVE LOGITS
    ания
    0.07
    ação
    0.07
    encias
    0.07
    FONT
    0.07
    建議
    0.07
    ание
    0.07
    diğiniz
    0.07
    껜
    0.07
    equal
    0.07
    ands
    0.07
    Act Density 0.016%

    No Known Activations