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

    Neuronpedia

    INDEX
    Explanations

    Non-English texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kỳ
    -0.07
     Terminal
    -0.06
    Traffic
    -0.06
    武
    -0.06
    ANI
    -0.06
    Construction
    -0.06
     differential
    -0.06
    446
    -0.06
     домов
    -0.05
     deficits
    -0.05
    POSITIVE LOGITS
    	BYTE
    0.07
     dib
    0.07
     appealing
    0.07
    _scalar
    0.07
    notations
    0.07
     scores
    0.07
     QLD
    0.07
    _rc
    0.07
    $b
    0.06
     anom
    0.06
    Act Density 0.028%

    No Known Activations