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

    Neuronpedia

    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Revenue
    -0.07
    těl
    -0.07
     Lia
    -0.07
    aigned
    -0.07
    das
    -0.07
     Whip
    -0.06
    Now
    -0.06
     revenue
    -0.06
     Restrictions
    -0.06
     lakh
    -0.06
    POSITIVE LOGITS
    toggle
    0.08
     chilled
    0.07
    /init
    0.06
    .il
    0.06
    .centerX
    0.06
     spices
    0.06
    迅
    0.06
     clic
    0.06
    [self
    0.06
    습
    0.06
    Act Density 0.011%

    No Known Activations