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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .svg
    -0.07
    Maria
    -0.06
    klär
    -0.06
    iar
    -0.06
    “These
    -0.06
     María
    -0.06
    Trou
    -0.06
    嘴
    -0.06
    Search
    -0.06
    戲
    -0.06
    POSITIVE LOGITS
     ست
    0.06
    dos
    0.06
    것
    0.06
    languages
    0.06
    _trampoline
    0.06
    ρια
    0.06
    러
    0.06
     ellipse
    0.06
     pep
    0.06
     tileSize
    0.06
    Act Density 0.083%

    No Known Activations