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

    Neuronpedia

    INDEX
    Explanations

    Old

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    larından
    -0.07
    	sys
    -0.07
     Gavin
    -0.07
     completo
    -0.07
    總統
    -0.07
    早在
    -0.07
    ,var
    -0.07
    شعور
    -0.07
    []↵
    -0.07
    草案
    -0.07
    POSITIVE LOGITS
     usability
    0.07
    .Gravity
    0.07
    cooldown
    0.07
    聆
    0.06
    aday
    0.06
    昼
    0.06
    鹴
    0.06
     Life
    0.06
    㧟
    0.06
    icum
    0.06
    Act Density 0.006%

    No Known Activations