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

    Neuronpedia

    INDEX
    Explanations

    status updates or capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     повторя
    0.47
    сер
    0.45
     कहा
    0.44
     llamados
    0.44
     exhibiting
    0.44
     уви
    0.44
     प्रदर्श
    0.43
    鲽
    0.43
     waving
    0.43
    রকম
    0.42
    POSITIVE LOGITS
    am
    0.49
    <0xE1>
    0.47
    ]{
    0.47
    an
    0.46
    -{
    0.46
    t
    0.46
    un
    0.45
    icina
    0.45
    eci
    0.45
    いが
    0.43
    Act Density 0.017%

    No Known Activations