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

    Neuronpedia

    INDEX
    Explanations

    sun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Salvador
    -0.09
     Glide
    -0.08
    sess
    -0.07
     З
    -0.07
     halten
    -0.07
     Beverage
    -0.07
    查看
    -0.07
    Portály
    -0.06
     مسائل
    -0.06
     dolay
    -0.06
    POSITIVE LOGITS
     sun
    0.07
    prus
    0.07
     Geoff
    0.06
    pi
    0.06
    _dirs
    0.06
     fourn
    0.06
     pau
    0.06
     Les
    0.06
     elif
    0.06
    944
    0.06
    Act Density 0.008%

    No Known Activations