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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Turner
    -0.06
     Vlad
    -0.06
    _signal
    -0.06
     publik
    -0.06
    úmer
    -0.06
    Mag
    -0.06
    numbers
    -0.06
    =config
    -0.06
    (ph
    -0.06
    /version
    -0.06
    POSITIVE LOGITS
     Sometimes
    0.07
    .Th
    0.06
    閉
    0.06
    ermann
    0.06
     informing
    0.06
    learning
    0.06
    Plus
    0.06
     anyway
    0.06
     ONE
    0.06
     Throughout
    0.06
    Act Density 0.000%

    No Known Activations