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

    Neuronpedia

    INDEX
    Explanations

    changes over time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َو
    -0.07
    COVID
    -0.06
    _configuration
    -0.06
     işe
    -0.06
    -sex
    -0.06
     dome
    -0.06
    DataSource
    -0.06
     تمام
    -0.06
    ndata
    -0.06
    aaaa
    -0.06
    POSITIVE LOGITS
     Bre
    0.07
     Skywalker
    0.07
    .package
    0.06
     Spit
    0.06
     Geg
    0.06
    ComputedStyle
    0.06
     muscle
    0.06
     feathers
    0.06
     Muscle
    0.06
     Αν
    0.06
    Act Density 0.054%

    No Known Activations