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

    Neuronpedia

    INDEX
    Explanations

    age and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    0.55
     modos
    0.52
    ন
    0.52
    л
    0.50
    к
    0.49
    ל
    0.48
    beds
    0.47
    मल
    0.47
     முதல்
    0.47
    ס
    0.47
    POSITIVE LOGITS
    trashItem
    0.48
    ری
    0.45
     كهرب
    0.45
    .";
    0.44
    یشه
    0.44
     நடை
    0.43
    andelion
    0.43
    اشی
    0.43
    EMPTY
    0.42
     Recognizing
    0.42
    Act Density 0.000%

    No Known Activations