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

    Neuronpedia

    INDEX
    Explanations

    email headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onun
    -0.06
     diverted
    -0.06
    oured
    -0.06
     이것
    -0.06
     Pratt
    -0.06
    ()%
    -0.06
     Carlo
    -0.06
    ۱۳۸
    -0.06
     sở
    -0.06
    けた
    -0.06
    POSITIVE LOGITS
    jít
    0.07
    catch
    0.06
     {})
    0.06
     stabilization
    0.06
    lict
    0.06
    _MATH
    0.06
    apis
    0.06
    '}
    0.06
     elimin
    0.06
    $class
    0.06
    Act Density 0.006%

    No Known Activations