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

    Neuronpedia

    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jerne
    -0.08
     scaleY
    -0.07
    출장
    -0.07
    [count
    -0.06
     примерно
    -0.06
    (floor
    -0.06
     인기
    -0.06
     toastr
    -0.06
     ReturnValue
    -0.06
     نسب
    -0.06
    POSITIVE LOGITS
    \Session
    0.07
     Claw
    0.07
     bude
    0.06
    regist
    0.06
    líž
    0.06
    GING
    0.06
     mum
    0.06
     Rest
    0.06
    agnitude
    0.06
     fucked
    0.06
    Act Density 0.096%

    No Known Activations