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

    Neuronpedia

    INDEX
    Explanations

    Negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     С
    -0.07
    ัด
    -0.06
    าส
    -0.06
     Пар
    -0.06
    _intervals
    -0.06
    -t
    -0.06
     Tories
    -0.06
    _timestamp
    -0.06
     conditions
    -0.06
     Furniture
    -0.06
    POSITIVE LOGITS
     divider
    0.07
    евые
    0.06
     ".$_
    0.06
     باشید
    0.06
    	Vector
    0.06
    plex
    0.06
    ран
    0.06
    oppins
    0.06
    _option
    0.06
    (This
    0.06
    Act Density 0.013%

    No Known Activations