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

    Neuronpedia

    INDEX
    Explanations

    data and dataset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.54
    8
    0.48
     và
    0.48
     are
    0.48
     ਅਤੇ
    0.47
     és
    0.47
    และ
    0.47
    0.44
     અને
    0.44
     thiab
    0.43
    POSITIVE LOGITS
    accouchement
    0.44
    aparikkh
    0.39
     iemand
    0.38
    证据
    0.38
    ставить
    0.38
     문제가
    0.38
    avacanam
    0.37
    这个人
    0.37
    ግኘት
    0.36
     ServicePolicy
    0.36
    Act Density 0.000%

    No Known Activations