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

    Neuronpedia

    INDEX
    Explanations

    Dimly lit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َم
    -0.08
    avir
    -0.07
    -sided
    -0.07
     Прод
    -0.07
    사회
    -0.07
    AspNet
    -0.06
     thriving
    -0.06
    째
    -0.06
     clean
    -0.06
    いて
    -0.06
    POSITIVE LOGITS
     lit
    0.09
    535
    0.07
     Mỹ
    0.07
    beth
    0.06
     repository
    0.06
     BAT
    0.06
     eats
    0.06
     jit
    0.06
     unavailable
    0.06
     LIC
    0.06
    Act Density 0.004%

    No Known Activations