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

    Neuronpedia

    INDEX
    Explanations

    LV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _matches
    -0.08
     meisten
    -0.08
    otec
    -0.07
     tre
    -0.07
    (sin
    -0.07
     Origin
    -0.07
    投身
    -0.07
     SearchResult
    -0.07
     Tec
    -0.07
    硒
    -0.07
    POSITIVE LOGITS
    otomy
    0.07
    垮
    0.06
    _ag
    0.06
    nano
    0.06
    ⏠
    0.06
    ό
    0.06
     palace
    0.06
    dıkl
    0.06
    쪗
    0.06
    料
    0.06
    Act Density 0.005%

    No Known Activations