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

    Neuronpedia

    INDEX
    Explanations

    references to licenses and related legal terms in the context of software

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

    web standards and licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.29
     cos
    -0.26
     out
    -0.26
     back
    -0.25
    std
    -0.25
    ↵
    -0.24
    该
    -0.23
    ec
    -0.23
    pos
    -0.23
    cos
    -0.23
    POSITIVE LOGITS
    GTCX
    0.85
    الحياه
    0.84
    <unused52>
    0.82
    <unused8>
    0.82
    <unused41>
    0.82
    <unused74>
    0.82
    rungsseite
    0.82
    <unused28>
    0.82
    <unused14>
    0.82
    <unused17>
    0.82
    Act Density 0.004%

    No Known Activations