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

    Neuronpedia

    INDEX
    Explanations

    instructions and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    horas
    0.87
    Hours
    0.86
    weeks
    0.86
     Week
    0.81
     Hours
    0.81
    Hrs
    0.80
    Week
    0.80
     недели
    0.79
     Tons
    0.78
     semanas
    0.78
    POSITIVE LOGITS
     എന്നാല്‍
    0.85
     वक़्त
    0.84
    Defence
    0.81
     oed
    0.80
    త్‌
    0.79
     കോണ്‍
    0.76
     своё
    0.75
     Communist
    0.75
     Chilli
    0.74
     Democratic
    0.74
    Act Density 0.000%

    No Known Activations