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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Subtract
    -0.08
    蔬菜
    -0.07
     subtraction
    -0.07
    芑
    -0.07
    湯
    -0.07
    _RETURNTRANSFER
    -0.07
    /send
    -0.07
    _dash
    -0.06
     domic
    -0.06
     suk
    -0.06
    POSITIVE LOGITS
     Chinese
    0.07
     MODE
    0.07
    手艺
    0.07
    ORT
    0.07
    짰
    0.07
     ports
    0.07
    melon
    0.07
     green
    0.07
     Pattern
    0.07
     Public
    0.07
    Act Density 0.002%

    No Known Activations