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

    Neuronpedia

    INDEX
    Explanations

    dialogue turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যাচাই
    0.45
     සහිත
    0.43
     পাইনি
    0.43
     simplify
    0.43
     genus
    0.43
     SCHEMA
    0.42
    応用
    0.42
     පිළ
    0.41
     সীমাবদ্ধ
    0.40
    相关的
    0.40
    POSITIVE LOGITS
     wrote
    0.82
     writes
    0.75
     says
    0.71
     пишет
    0.69
     berkata
    0.68
     scrive
    0.65
     escribió
    0.64
     skrev
    0.63
     schreibt
    0.62
     schrieb
    0.61
    Act Density 0.010%

    No Known Activations