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

    Neuronpedia

    INDEX
    Explanations

    $. We

    np_acts-logits-general · gemini-2.5-flash-lite

    the closing of inline LaTeX math (a dollar sign directly followed by sentence-ending punctuation).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Hermione
    0.47
     Remaining
    0.45
     garis
    0.45
    .${
    0.44
     jalur
    0.44
    ENES
    0.43
    ApiClient
    0.42
    নু
    0.42
    員工
    0.42
    ۣ
    0.42
    POSITIVE LOGITS
    hyp
    0.41
    imagine
    0.40
    training
    0.40
    save
    0.39
    trained
    0.39
     truly
    0.39
    modulated
    0.38
    kow
    0.38
    ydro
    0.38
    sold
    0.38
    Act Density 0.000%

    No Known Activations