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

    Neuronpedia

    INDEX
    Explanations

    licensing and developer tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حق
    0.41
     בת
    0.39
    hak
    0.39
     MIM
    0.37
     Sikk
    0.36
     vorg
    0.36
    ี่ยง
    0.36
     przest
    0.36
     Getty
    0.36
     تاب
    0.36
    POSITIVE LOGITS
     फिज
    0.42
    মধ
    0.41
    িয়াছিল
    0.41
     выбрали
    0.41
     физи
    0.39
    ͉
    0.39
    Сред
    0.39
    сред
    0.39
     frère
    0.38
    wave
    0.38
    Act Density 0.000%

    No Known Activations