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

    Neuronpedia

    INDEX
    Explanations

    phone numbers or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ltk
    0.38
    偣
    0.38
    ைகள
    0.37
    läufig
    0.35
    шив
    0.35
    ьи
    0.35
     adoptar
    0.35
     SimSun
    0.34
    рая
    0.33
     الشكل
    0.33
    POSITIVE LOGITS
     Modal
    0.40
    月から
    0.36
    次に
    0.36
    ूर्
    0.36
    க்கோ
    0.36
     Chloride
    0.35
    ㄏ
    0.35
     IDA
    0.35
    ————————
    0.34
     Calendar
    0.34
    Act Density 0.005%

    No Known Activations