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

    Neuronpedia

    INDEX
    Explanations

    Interestingly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ковод
    -0.07
    нання
    -0.06
     выбра
    -0.06
     clinics
    -0.06
     خدم
    -0.06
    ære
    -0.06
    ábado
    -0.06
    _added
    -0.05
     letz
    -0.05
     ck
    -0.05
    POSITIVE LOGITS
     seiz
    0.08
    drawing
    0.07
     Halo
    0.07
     COR
    0.07
     Authentic
    0.07
     CART
    0.07
     BAB
    0.07
    expression
    0.07
    697
    0.06
     SZ
    0.06
    Act Density 0.008%

    No Known Activations