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

    Neuronpedia

    INDEX
    Explanations

    quotes/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counsel
    -0.08
     measures
    -0.08
     Counsel
    -0.07
     Deferred
    -0.07
     simplic
    -0.07
     Measures
    -0.07
    sein
    -0.07
    ukur
    -0.07
     artillery
    -0.07
     talked
    -0.07
    POSITIVE LOGITS
    abcdefghijklmnopqrstuvwxyz
    0.11
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.11
    abcdefghijkl
    0.10
    owels
    0.09
     문자열
    0.09
     목록
    0.09
     digits
    0.09
     переч
    0.09
    digits
    0.09
    _digits
    0.08
    Act Density 0.007%

    No Known Activations