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

    Neuronpedia

    INDEX
    Explanations

    employers' contexts and expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '
    -2.69
    絰
    -2.44
    '
    -2.42
    y
    -2.36
    ть
    -2.23
    i
    -2.16
     It
    -2.08
    2
    -2.08
    ".
    -2.06
    という言葉
    -2.06
    POSITIVE LOGITS
    ﹍﹍
    2.70
    狆
    2.56
    ,’
    2.34
    枼
    2.19
    嫒
    2.17
    ℣
    2.08
    jaqueta
    2.06
    猡
    2.06
     eighty
    2.05
    淠
    2.05
    Act Density 0.005%

    No Known Activations