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

    Neuronpedia

    INDEX
    Explanations

    programming references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iata
    -0.08
     uncover
    -0.08
    konto
    -0.08
     מלאה
    -0.08
    iant
    -0.07
    forall
    -0.07
    ikä
    -0.07
    iterr
    -0.07
    Inflater
    -0.07
    istaa
    -0.07
    POSITIVE LOGITS
     объектов
    0.09
     objects
    0.09
    objects
    0.09
     Frag
    0.09
     वस्त
    0.09
     objetos
    0.08
     traced
    0.08
     bacter
    0.08
     objek
    0.08
     fragile
    0.08
    Act Density 0.004%

    No Known Activations