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

    Neuronpedia

    INDEX
    Explanations

    return statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gave
    0.50
    gives
    0.49
     gives
    0.44
    過的
    0.43
    <0xAC>
    0.43
    output
    0.43
     lends
    0.41
     প্রভৃতির
    0.41
     받을
    0.41
    צב
    0.41
    POSITIVE LOGITS
    return
    1.20
     return
    1.18
     Return
    0.88
    Return
    0.78
     retorn
    0.78
     RETURN
    0.77
     возвра
    0.74
     retorno
    0.74
     retour
    0.72
     retornar
    0.71
    Act Density 0.168%

    No Known Activations