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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    �
    -0.07
     ул
    -0.06
    Dan
    -0.06
     Astros
    -0.06
    айте
    -0.06
     Dan
    -0.06
    &display
    -0.06
     Haz
    -0.06
    hib
    -0.06
    POSITIVE LOGITS
    牌
    0.07
    (propertyName
    0.07
    aların
    0.07
    cg
    0.06
    ंग
    0.06
     individually
    0.06
    lerdi
    0.06
     Carter
    0.06
    τερ
    0.06
     caregiver
    0.06
    Act Density 0.142%

    No Known Activations