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

    Neuronpedia

    INDEX
    Explanations

    actions between entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.48
     Waterproof
    0.46
    вым
    0.45
    ቀም
    0.45
     বেশি
    0.45
    ']}")
    0.44
     بیشتر
    0.44
    ню
    0.44
    ˧
    0.44
     них
    0.43
    POSITIVE LOGITS
     terhadap
    0.70
     of
    0.68
    로부터
    0.68
     from
    0.66
     från
    0.65
     ofthe
    0.64
    으로부터
    0.61
     από
    0.59
    による
    0.59
     undertaken
    0.57
    Act Density 0.009%

    No Known Activations