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

    Neuronpedia

    INDEX
    Explanations

    population statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MeasureSpec
    -0.07
     Investors
    -0.07
     ensured
    -0.06
     Billy
    -0.06
    mr
    -0.06
     Afro
    -0.06
    byt
    -0.06
    �
    -0.06
    Billy
    -0.06
    Seats
    -0.06
    POSITIVE LOGITS
     protests
    0.07
    asion
    0.07
     kırmızı
    0.07
     griev
    0.06
     نظری
    0.06
    threat
    0.06
    phant
    0.06
     subtotal
    0.06
     guard
    0.06
     Relay
    0.06
    Act Density 0.001%

    No Known Activations