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

    Neuronpedia

    INDEX
    Explanations

    how things function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (hit
    -0.06
     Sticky
    -0.06
     Prosper
    -0.06
    chap
    -0.06
    icers
    -0.06
    wipe
    -0.06
     Positive
    -0.06
     badly
    -0.06
    Rank
    -0.06
     ""},↵
    -0.06
    POSITIVE LOGITS
    _expand
    0.06
    _adjust
    0.06
    터
    0.06
    การเล
    0.06
    침
    0.06
     شي
    0.06
    !(
    0.06
     modular
    0.06
    _WIN
    0.06
    _upgrade
    0.06
    Act Density 0.107%

    No Known Activations