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

    Neuronpedia

    INDEX
    Explanations

    in terms of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kungan
    0.76
    ñas
    0.73
     láp
    0.73
     أثناء
    0.72
     lanzó
    0.71
    arrerol
    0.71
    úly
    0.71
    매
    0.70
     دون
    0.69
    uddin
    0.68
    POSITIVE LOGITS
     terms
    2.34
    terms
    2.00
     Terms
    1.98
    Terms
    1.77
     TERMS
    1.72
     termes
    1.69
     term
    1.59
     términos
    1.58
     termini
    1.50
     termos
    1.49
    Act Density 0.097%

    No Known Activations