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

    Neuronpedia

    INDEX
    Explanations

    Lin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     درون
    -0.07
    input
    -0.07
    つ
    -0.07
     insisting
    -0.07
     recycled
    -0.07
     wars
    -0.06
     fullWidth
    -0.06
    remium
    -0.06
     Гор
    -0.06
     mkdir
    -0.06
    POSITIVE LOGITS
    LATED
    0.07
    peration
    0.06
    LEY
    0.06
    erral
    0.06
    .SM
    0.06
    !)
    0.06
    Autor
    0.06
    імеч
    0.06
    (package
    0.06
    รณ
    0.06
    Act Density 0.052%

    No Known Activations