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

    Neuronpedia

    INDEX
    Explanations

    Technical/Astrological jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     huel
    -0.08
     Cic
    -0.08
    Nation
    -0.07
     परेशान
    -0.07
     flam
    -0.07
     hypert
    -0.07
    ാണ
    -0.07
    ಾಟ್
    -0.07
     Arist
    -0.07
     casual
    -0.07
    POSITIVE LOGITS
     aliqu
    0.08
     mérito
    0.08
     PROVID
    0.07
    惜
    0.07
     Polisi
    0.07
     PERFORMANCE
    0.07
    onza
    0.07
     QLabel
    0.07
    وں
    0.07
    press
    0.07
    Act Density 0.000%

    No Known Activations