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

    Neuronpedia

    INDEX
    Explanations

    list separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    variant
    -0.07
    (attr
    -0.07
     ML
    -0.06
     Variation
    -0.06
     rowCount
    -0.06
     propositions
    -0.06
    _MAY
    -0.06
     był
    -0.06
     Furn
    -0.06
    chedulers
    -0.06
    POSITIVE LOGITS
    /from
    0.07
    exels
    0.07
     combustion
    0.06
    	fire
    0.06
     القرن
    0.06
     прежде
    0.06
     gunfire
    0.06
     Ans
    0.06
     Goblin
    0.06
     CLEAR
    0.06
    Act Density 0.089%

    No Known Activations