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

    Neuronpedia

    INDEX
    Explanations

    AI enhancing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     केस
    0.49
     👋
    0.49
     protección
    0.46
     ivvu
    0.46
    Entonces
    0.46
    RationalValue
    0.44
     ऑप्शन
    0.44
     Orden
    0.44
    forcement
    0.43
     Caso
    0.43
    POSITIVE LOGITS
    by
    0.54
     by
    0.47
    iaal
    0.44
    ໂດຍ
    0.44
    ian
    0.44
    ana
    0.41
     devoted
    0.41
     years
    0.41
    िडेट
    0.41
    downs
    0.41
    Act Density 0.001%

    No Known Activations