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

    Neuronpedia

    INDEX
    Explanations

    making things better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    மானது
    0.78
    包含了
    0.76
    മാണ്
    0.75
    हमने
    0.72
    Стро
    0.72
     सच्चाई
    0.69
    ைகளில்
    0.68
     предоставляет
    0.68
    ങ്ങളാണ്
    0.67
     বলছে
    0.66
    POSITIVE LOGITS
     happen
    2.00
     disappear
    1.92
     appear
    1.89
     vanish
    1.77
     occur
    1.67
     thrive
    1.61
     survive
    1.60
     feel
    1.58
     seem
    1.53
     emerge
    1.52
    Act Density 0.118%

    No Known Activations