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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /pdf
    -0.07
     peaked
    -0.07
    enser
    -0.06
     mural
    -0.06
    ρας
    -0.06
    UsageId
    -0.06
     pinterest
    -0.06
     Bord
    -0.06
     Bis
    -0.06
     боку
    -0.06
    POSITIVE LOGITS
    347
    0.07
     cheg
    0.06
     opět
    0.06
    /component
    0.06
    .spacing
    0.06
     Sau
    0.06
    @js
    0.06
     ERROR
    0.06
    (Action
    0.06
    PPER
    0.06
    Act Density 0.004%

    No Known Activations