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

    Neuronpedia

    INDEX
    Explanations

    injured people and victims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    보
    0.44
    让
    0.44
     দিনের
    0.44
    经验
    0.44
    -
    0.43
    :
    0.42
    Sch
    0.40
     그것
    0.40
     आणि
    0.40
    包括
    0.40
    POSITIVE LOGITS
     actuellement
    0.49
    加入了
    0.46
    dotted
    0.44
     idk
    0.44
     ständig
    0.43
     fréquemment
    0.43
     precarious
    0.43
     appartenant
    0.43
     touted
    0.42
     purportedly
    0.42
    Act Density 0.004%

    No Known Activations