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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ở
    -0.06
     petition
    -0.06
     prol
    -0.06
     exposed
    -0.06
    They
    -0.06
    ки
    -0.06
     advertised
    -0.06
    _DGRAM
    -0.06
    [class
    -0.06
     ACT
    -0.06
    POSITIVE LOGITS
     praw
    0.07
    ै।↵↵
    0.07
    였
    0.06
    	logging
    0.06
     şart
    0.06
    []);↵
    0.06
    独
    0.06
    _probs
    0.06
     Fund
    0.06
     "-"↵
    0.06
    Act Density 0.000%

    No Known Activations