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

    Neuronpedia

    INDEX
    Explanations

    Code installation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ida
    -0.08
    .CharField
    -0.08
    дов
    -0.07
     harm
    -0.07
    weigh
    -0.06
     Rivera
    -0.06
     ≥
    -0.06
    allen
    -0.06
    력
    -0.06
     viên
    -0.06
    POSITIVE LOGITS
    .which
    0.08
     "'
    0.06
     Gio
    0.06
     Rabbit
    0.06
     )))
    0.06
    uan
    0.06
    θλη
    0.06
    pler
    0.06
    　j
    0.06
    γκε
    0.06
    Act Density 0.067%

    No Known Activations