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

    Neuronpedia

    INDEX
    Explanations

    pauses and trailing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     awesome
    0.78
    めっちゃ
    0.77
    啥
    0.77
     dudes
    0.72
     dude
    0.72
     banget
    0.60
     Awesome
    0.57
     aka
    0.55
    awesome
    0.55
     weird
    0.54
    POSITIVE LOGITS
    -”
    0.86
    …”
    0.82
    —”
    0.78
    ...”
    0.73
    …"
    0.67
    …
    0.66
    ?”
    0.66
    ..”
    0.64
    --’
    0.64
    --"
    0.62
    Act Density 0.334%

    No Known Activations