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

    Neuronpedia

    INDEX
    Explanations

    action and economic context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     projektu
    -0.07
    akh
    -0.07
    Shadow
    -0.07
    ampion
    -0.06
    _sibling
    -0.06
    kové
    -0.06
     부분
    -0.06
    595
    -0.06
     quand
    -0.06
     čís
    -0.06
    POSITIVE LOGITS
    .radio
    0.07
     Fence
    0.07
    ={$
    0.06
    -----↵
    0.06
    [out
    0.06
     JUL
    0.06
    漂
    0.06
    (any
    0.06
     '%$
    0.06
    -->
↵
    0.06
    Act Density 0.064%

    No Known Activations