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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सम्मिलित
    0.41
    émi
    0.41
     melaksanakan
    0.40
    êts
    0.40
     gad
    0.40
    被迫
    0.40
     Nasional
    0.39
     GAAP
    0.39
    вати
    0.39
     typology
    0.39
    POSITIVE LOGITS
    comma
    0.49
    속
    0.46
    ژن
    0.46
    ロシア
    0.44
    compatibility
    0.43
     челу
    0.43
    favor
    0.43
    غیر
    0.42
    Transfer
    0.42
    revoke
    0.42
    Act Density 0.007%

    No Known Activations