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

    Neuronpedia

    INDEX
    Explanations

    asking what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Click
    0.67
     desired
    0.66
     خواہش
    0.64
    মার
    0.63
     worshi
    0.63
     is
    0.62
    click
    0.62
    ETIC
    0.62
     tingling
    0.61
     gong
    0.61
    POSITIVE LOGITS
    ezas
    0.83
     consigui
    0.82
     добре
    0.80
     মৃতের
    0.80
    rimps
    0.78
     এপ
    0.78
     verkauft
    0.78
     sucesivamente
    0.77
     справ
    0.77
     consigue
    0.77
    Act Density 0.062%

    No Known Activations