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

    Neuronpedia

    INDEX
    Explanations

    alcohol risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (coordinates
    -0.07
     strang
    -0.07
     vign
    -0.07
     backbone
    -0.06
    /V
    -0.06
     garn
    -0.06
    Suffix
    -0.06
    _MEMORY
    -0.06
    🎊
    -0.06
    ":↵↵
    -0.06
    POSITIVE LOGITS
    𬱖
    0.07
    opensource
    0.07
    ▲
    0.07
    ặc
    0.07
     못
    0.07
    //----------------------------------------------------------------------------
    0.07
     preco
    0.06
    菜
    0.06
    GER
    0.06
    يم
    0.06
    Act Density 0.027%

    No Known Activations