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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ForCanBeConvertedToF
    -0.07
    (pi
    -0.06
    unifu
    -0.06
    ponent
    -0.06
     smoothly
    -0.06
    .has
    -0.06
    layan
    -0.06
    LOAT
    -0.05
    {:
    -0.05
    ]=(
    -0.05
    POSITIVE LOGITS
    烟
    0.08
    baar
    0.07
    atars
    0.07
    ups
    0.07
    ’am
    0.07
     गर
    0.07
     домашних
    0.07
    τηκε
    0.07
    َي
    0.06
    uppy
    0.06
    Act Density 0.003%

    No Known Activations