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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .exec
    -0.07
    ImageContext
    -0.07
    _Of
    -0.07
    exec
    -0.07
    Maps
    -0.07
    _CI
    -0.07
     forte
    -0.07
     hóa
    -0.07
    ampaign
    -0.07
     Balt
    -0.07
    POSITIVE LOGITS
     number
    0.08
             ↵
    0.06
     pornos
    0.06
    ्बन
    0.06
     děti
    0.06
    iscing
    0.06
    #
↵
    0.06
    laughs
    0.06
    лено
    0.06
     akıl
    0.06
    Act Density 0.035%

    No Known Activations