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

    Neuronpedia

    INDEX
    Explanations

    -root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gu
    -0.07
    compass
    -0.07
     sparkling
    -0.07
    resent
    -0.06
    Electric
    -0.06
     вони
    -0.06
     liv
    -0.06
    Special
    -0.06
     lis
    -0.06
     began
    -0.06
    POSITIVE LOGITS
     نخ
    0.07
    _UNS
    0.06
     Ret
    0.06
    Drink
    0.06
     тобі
    0.06
     Join
    0.06
     /\
    0.06
    วรร
    0.06
    ™
    0.06
    ailing
    0.06
    Act Density 0.000%

    No Known Activations