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

    Neuronpedia

    INDEX
    Explanations

    Basis of you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embellished
    0.49
     elementi
    0.49
     elaborated
    0.49
     earbuds
    0.48
     Лон
    0.48
     отличается
    0.47
     reúne
    0.47
     малень
    0.47
     mudanças
    0.47
     perguntas
    0.47
    POSITIVE LOGITS
    frac
    0.52
    tests
    0.46
    Y
    0.46
    iy
    0.46
    iky
    0.45
    that
    0.45
    .
    0.44
    T
    0.44
    Cl
    0.44
    Function
    0.44
    Act Density 0.003%

    No Known Activations