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

    Neuronpedia

    INDEX
    Explanations

    /s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fwrite
    -0.07
     kelim
    -0.07
    /utils
    -0.07
    THING
    -0.07
    řila
    -0.06
    ライン
    -0.06
    iced
    -0.06
    Adds
    -0.06
    positor
    -0.06
    ो,
    -0.06
    POSITIVE LOGITS
     john
    0.06
    visited
    0.06
     grit
    0.06
    iž
    0.06
    /><
    0.06
    戒
    0.06
    口
    0.06
    놓
    0.06
     sitio
    0.06
    观看
    0.06
    Act Density 0.049%

    No Known Activations