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

    Neuronpedia

    INDEX
    Explanations

    multilingual words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EMENTS
    0.45
    ARR
    0.44
    ptuous
    0.41
    ous
    0.40
     encirc
    0.40
    destructive
    0.39
     arrhyth
    0.38
     શ્રે
    0.38
    oxyphenyl
    0.38
     cytoplasm
    0.38
    POSITIVE LOGITS
     škola
    0.38
    രുന്നു
    0.37
     thrives
    0.36
     चैंपियन
    0.36
     мной
    0.35
     conosce
    0.35
    뵙
    0.35
    Emergency
    0.35
     وتش
    0.35
    kowo
    0.34
    Act Density 0.005%

    No Known Activations