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

    Neuronpedia

    INDEX
    Explanations

    supplying separately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     లో
    0.41
     පහ
    0.40
     स्वागत
    0.38
     invocation
    0.38
     বিক্ষোভ
    0.38
     поведение
    0.37
     մի
    0.37
     явно
    0.36
     వైసీపీ
    0.36
    ள
    0.36
    POSITIVE LOGITS
     réun
    0.46
     and
    0.46
     અને
    0.41
     months
    0.41
     professionally
    0.39
     collectif
    0.39
     intensa
    0.39
     riun
    0.39
    và
    0.38
     και
    0.38
    Act Density 0.001%

    No Known Activations