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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கேரள
    0.54
     சிகி
    0.50
    tpVar
    0.50
     कर्फ
    0.49
    createElement
    0.48
     ফ্র
    0.47
     रीजनिंग
    0.46
     علمی
    0.46
    াতাড়ি
    0.46
     öffentliche
    0.46
    POSITIVE LOGITS
    ↵↵
    0.50
    प
    0.49
    م
    0.47
     hetzelfde
    0.43
     Probe
    0.43
     Simple
    0.42
    Simple
    0.42
    पो
    0.42
    بس
    0.41
    ,
    0.41
    Act Density 0.000%

    No Known Activations