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

    Neuronpedia

    INDEX
    Explanations

    numerical ratings and evaluative expressions related to quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    star ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -1.04
     otomatig
    -0.90
    <unused41>
    -0.88
    <unused28>
    -0.88
     تضيفلها
    -0.88
    <unused68>
    -0.88
    [@BOS@]
    -0.88
    <unused47>
    -0.87
    <unused16>
    -0.87
    <unused3>
    -0.87
    POSITIVE LOGITS
    『
    0.22
    J
    0.22
    NotEqualTo
    0.21
    OrUpdate
    0.21
     Mike
    0.21
     pank
    0.21
    /*
    0.20
    </em>
    0.20
    Affirmed
    0.20
    Perf
    0.19
    Act Density 0.003%

    No Known Activations