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

    Neuronpedia

    INDEX
    Explanations

    f string formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     своїх
    0.39
     сві
    0.38
     מי
    0.34
     большой
    0.34
     प्रजनन
    0.34
     thèse
    0.33
     심
    0.32
     числе
    0.32
     diá
    0.32
     ઘણા
    0.32
    POSITIVE LOGITS
    s
    0.49
    name
    0.47
    no
    0.45
    null
    0.43
    x
    0.43
    in
    0.42
    i
    0.42
    on
    0.42
    os
    0.42
    na
    0.41
    Act Density 0.035%

    No Known Activations