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

    Neuronpedia

    INDEX
    Explanations

    event handlers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (my
    -0.07
     leap
    -0.07
    (pi
    -0.07
     intervene
    -0.06
     seen
    -0.06
     rew
    -0.06
    	real
    -0.06
     hipp
    -0.06
    (equal
    -0.06
     depicts
    -0.06
    POSITIVE LOGITS
     onChange
    0.08
     onClick
    0.07
    	onClick
    0.07
     zdarma
    0.07
    чай
    0.07
     hurricanes
    0.07
    SG
    0.06
    上海
    0.06
    àng
    0.06
     ott
    0.06
    Act Density 0.008%

    No Known Activations