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

    Neuronpedia

    INDEX
    Explanations

    references to common weakness enumerations (CWEs) related to software vulnerabilities

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

    backup qb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.12
     المعيارى
    -0.94
     שוליים
    -0.89
    ロウィン
    -0.87
    <unused28>
    -0.87
    <unused23>
    -0.87
    <unused41>
    -0.87
    <unused43>
    -0.87
    <unused14>
    -0.87
    <unused17>
    -0.87
    POSITIVE LOGITS
    Conv
    0.31
    通
    0.24
    pen
    0.22
     Recently
    0.20
     “
    0.20
    ACIO
    0.20
     continual
    0.20
    能在
    0.20
    sn
    0.19
     reine
    0.19
    Act Density 0.002%

    No Known Activations