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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mga
    -0.10
    們
    -0.10
     berbagai
    -0.09
     various
    -0.09
    Various
    -0.09
     Alias
    -0.09
    们
    -0.08
    各种
    -0.08
    τικό
    -0.08
     Various
    -0.08
    POSITIVE LOGITS
     подряд
    0.16
     tegelijk
    0.15
     각각
    0.12
    分别
    0.12
     모두
    0.12
     plus
    0.11
     consecut
    0.11
    以内
    0.10
    씩
    0.10
     interconnected
    0.10
    Act Density 0.434%

    No Known Activations