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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     هاي
    -0.06
    (infile
    -0.06
    �数
    -0.06
     �
    -0.06
    �
    -0.06
     Bare
    -0.06
    /Y
    -0.06
    habi
    -0.06
     дней
    -0.06
    .more
    -0.06
    POSITIVE LOGITS
     Qualified
    0.07
     ES
    0.07
    λικ
    0.07
     Labels
    0.07
     Victims
    0.06
     Discover
    0.06
    Protect
    0.06
     audi
    0.06
    .At
    0.06
     Correspond
    0.06
    Act Density 0.006%

    No Known Activations