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

    Neuronpedia

    INDEX
    Explanations

    inauguration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     challenge
    -0.07
     sense
    -0.07
    please
    -0.07
     peque
    -0.06
     финансов
    -0.06
     rod
    -0.06
     chip
    -0.06
     leveled
    -0.06
     dell
    -0.06
     challenged
    -0.06
    POSITIVE LOGITS
     inauguration
    0.09
    Ag
    0.07
     inaugur
    0.07
    lsruhe
    0.07
    нул
    0.06
     Προ
    0.06
    Τα
    0.06
     тисяч
    0.06
     посад
    0.06
     equitable
    0.06
    Act Density 0.002%

    No Known Activations