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

    Neuronpedia

    INDEX
    Explanations

    Vietnamese, Arabic, Cyrillic scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.77
    u
    0.71
    at
    0.67
     menjalani
    0.64
     SaaS
    0.62
     segu
    0.61
     makeshift
    0.61
     readership
    0.59
     robotic
    0.58
     robotics
    0.57
    POSITIVE LOGITS
     and
    0.72
     it
    0.66
     is
    0.63
     of
    0.61
    ري
    0.60
    ديد
    0.59
    ко
    0.58
     antiguos
    0.58
    كم
    0.56
    มัน
    0.56
    Act Density 0.086%

    No Known Activations