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

    Neuronpedia

    INDEX
    Explanations

    numbers or identifiers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused1854>
    0.43
    <unused458>
    0.42
    <unused757>
    0.41
    <unused164>
    0.41
    8
    0.41
    <unused1974>
    0.41
    ால்
    0.41
    <unused260>
    0.40
    <unused303>
    0.40
    <unused557>
    0.40
    POSITIVE LOGITS
    ॰
    0.45
     کاسینو
    0.45
    .,
    0.44
    .-
    0.41
    ._
    0.41
    .),
    0.39
     supporter
    0.39
    פי
    0.38
     principal
    0.38
    .$-
    0.38
    Act Density 0.105%

    No Known Activations