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

    Neuronpedia

    INDEX
    Explanations

    fake check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मंत्र
    0.40
    シャフト
    0.37
     stoves
    0.36
    oxing
    0.36
     Neck
    0.35
    Treas
    0.35
    ίνει
    0.35
    box
    0.35
    खाने
    0.35
     सैलरी
    0.34
    POSITIVE LOGITS
     unto
    0.50
     पाप
    0.41
     Laura
    0.39
     produzido
    0.39
    Mood
    0.37
    òu
    0.37
    യം
    0.37
    Balances
    0.37
    浥
    0.37
    াজের
    0.36
    Act Density 0.008%

    No Known Activations