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

    Neuronpedia

    INDEX
    Explanations

    scientific papers authors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sick
    -0.07
     前
    -0.06
     mand
    -0.06
     grades
    -0.06
     panc
    -0.06
    ่าม
    -0.06
     count
    -0.06
     Manga
    -0.06
     expelled
    -0.06
    สมาช
    -0.06
    POSITIVE LOGITS
    navbar
    0.07
    .hxx
    0.07
     geht
    0.06
    _bins
    0.06
    @Data
    0.06
    lacağı
    0.06
    csr
    0.06
    _chunks
    0.06
    onse
    0.06
     olmasına
    0.06
    Act Density 0.001%

    No Known Activations