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

    Neuronpedia

    INDEX
    Explanations

    Formal writing/research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minValue
    -0.07
    -Speed
    -0.07
    Productos
    -0.07
    adastro
    -0.07
     Nghị
    -0.07
    癍
    -0.07
    购车
    -0.06
    โครงการ
    -0.06
    aData
    -0.06
    otions
    -0.06
    POSITIVE LOGITS
     keys
    0.08
    .lock
    0.08
    .Bl
    0.07
    .git
    0.07
     Perry
    0.07
    '));↵
    0.07
     Elvis
    0.07
     Buck
    0.07
    上传
    0.07
    drFc
    0.07
    Act Density 0.374%

    No Known Activations