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

    Neuronpedia

    INDEX
    Explanations

    UR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    луги
    -0.06
    Adam
    -0.06
    +"_
    -0.06
     رضا
    -0.06
     lm
    -0.06
     Damen
    -0.06
     форма
    -0.06
     POSSIBILITY
    -0.06
     preceded
    -0.06
     मण
    -0.06
    POSITIVE LOGITS
    Roll
    0.07
    [...,
    0.07
    инг
    0.06
     egg
    0.06
    友
    0.06
    ophobic
    0.06
     디
    0.06
     перемен
    0.06
    录
    0.06
    forcing
    0.06
    Act Density 0.001%

    No Known Activations