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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     //_
    -0.07
     rebel
    -0.06
    itzerland
    -0.06
    News
    -0.06
     fld
    -0.06
     în
    -0.06
    _iteration
    -0.06
    quo
    -0.06
    =x
    -0.06
     nga
    -0.06
    POSITIVE LOGITS
     sik
    0.07
     Seriously
    0.07
    '/>↵
    0.07
    AndHashCode
    0.07
    !",
    0.07
     çocu
    0.07
    %D
    0.06
    ?',↵
    0.06
     Güney
    0.06
    àu
    0.06
    Act Density 0.002%

    No Known Activations