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

    Neuronpedia

    INDEX
    Explanations

    frontal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    簡
    -0.09
    ं
    -0.08
     accidentes
    -0.08
    _serial
    -0.08
     gravy
    -0.07
     ceil
    -0.07
    antics
    -0.07
    Packets
    -0.07
    iscos
    -0.07
     hashing
    -0.07
    POSITIVE LOGITS
     exert
    0.12
    	control
    0.11
     नियंत्रण
    0.10
     നിയന്ത്ര
    0.10
     control
    0.10
     controla
    0.10
    /control
    0.09
    Control
    0.09
     controllo
    0.09
     Kontrolle
    0.09
    Act Density 0.004%

    No Known Activations