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

    Neuronpedia

    INDEX
    Explanations

    spends more, Rome maintained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Clipboard
    0.42
    וב
    0.42
    שה
    0.41
    ༡
    0.40
    ே
    0.39
     মাছ
    0.38
    १
    0.38
    ptosis
    0.38
    க்கூடாது
    0.38
     కేసు
    0.38
    POSITIVE LOGITS
     inaugural
    0.44
     commencement
    0.42
     chẳng
    0.41
     connecting
    0.41
     domingo
    0.41
     programs
    0.40
    mint
    0.40
     activités
    0.39
     importanti
    0.39
     tutoring
    0.39
    Act Density 0.009%

    No Known Activations