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

    Neuronpedia

    INDEX
    Explanations

    science and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    いつ
    -0.07
    チ
    -0.07
     reach
    -0.07
     правил
    -0.06
    じ
    -0.06
    Five
    -0.06
     cứ
    -0.06
    어진
    -0.06
    された
    -0.06
    atching
    -0.06
    POSITIVE LOGITS
     ]]↵
    0.07
     لغ
    0.07
     dele
    0.07
    _datas
    0.06
    %)↵↵
    0.06
     dame
    0.06
    ied
    0.06
     円
    0.06
     タ
    0.06
     activ
    0.06
    Act Density 0.089%

    No Known Activations