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

    Neuronpedia

    INDEX
    Explanations

    p, modulus, charge, formula

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     countries
    0.58
     países
    0.54
     provinces
    0.48
    africa
    0.48
     multinationals
    0.46
     असतात
    0.45
     Countries
    0.44
     compañías
    0.44
     precedes
    0.44
     ambitions
    0.44
    POSITIVE LOGITS
    addItem
    0.43
    തോ
    0.42
    饵
    0.42
    zelfde
    0.41
    inite
    0.40
    原有
    0.40
     Mound
    0.40
     Quindi
    0.40
     نئی
    0.40
     και
    0.39
    Act Density 0.005%

    No Known Activations