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

    Neuronpedia

    INDEX
    Explanations

    dialogue endings with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.49
     (
    0.46
     بنایا
    0.41
     insulation
    0.40
     hopper
    0.40
     ventilation
    0.39
     redox
    0.38
    (),
    0.38
     greatest
    0.38
     liability
    0.37
    POSITIVE LOGITS
    “…
    0.52
    𝑻
    0.51
    "...
    0.48
    Ми
    0.47
     "...
    0.47
    श्री
    0.47
    )...
    0.46
    嘿
    0.46
    𝚃
    0.46
     “…
    0.45
    Act Density 0.002%

    No Known Activations