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

    Neuronpedia

    INDEX
    Explanations

    Data and indices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Love
    -0.07
    ticks
    -0.07
    끼
    -0.07
    	Double
    -0.07
    ichert
    -0.07
    -but
    -0.07
     :/
    -0.06
    ย
    -0.06
    save
    -0.06
     apk
    -0.06
    POSITIVE LOGITS
     ویژگی
    0.07
     месте
    0.06
     다시
    0.06
    BOOLE
    0.06
     dividends
    0.06
    usual
    0.06
     estud
    0.06
     кирп
    0.06
     agricult
    0.06
    .blank
    0.06
    Act Density 0.018%

    No Known Activations