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

    Neuronpedia

    INDEX
    Explanations

    unilateral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grains
    -0.08
     sau
    -0.08
     ಬಳಿ
    -0.08
     picky
    -0.07
     Т
    -0.07
    MJ
    -0.07
     Tampa
    -0.07
    door
    -0.07
    achter
    -0.07
    	debug
    -0.07
    POSITIVE LOGITS
     действий
    0.10
    休日
    0.09
     effort
    0.08
     நடவட
    0.08
     операций
    0.08
    -owned
    0.08
    広
    0.07
     પ્રયાસ
    0.07
     unilateral
    0.07
    mente
    0.07
    Act Density 0.001%

    No Known Activations