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

    Neuronpedia

    INDEX
    Explanations

    primary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    běh
    -0.07
     nastav
    -0.07
    裡
    -0.07
    轉
    -0.06
     里
    -0.06
    isinden
    -0.06
    笔
    -0.06
     liter
    -0.06
    δόν
    -0.06
    jar
    -0.06
    POSITIVE LOGITS
     primary
    0.12
     Primary
    0.09
    Cookie
    0.08
    :E
    0.07
    >",
    0.07
    provider
    0.07
    '}}>↵
    0.07
    primary
    0.07
     preference
    0.07
    ıldığında
    0.06
    Act Density 0.010%

    No Known Activations