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

    Neuronpedia

    INDEX
    Explanations

    phrases related to incidents or events, particularly those involving crime or accidents

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

    この following の

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.30
    RenderAtEndOf
    -0.30
     ويكيپيديا
    -0.30
     ways
    -0.30
     iNdEx
    -0.29
    せよ
    -0.27
     ModelExpression
    -0.27
     poursuite
    -0.27
    ’
    -0.26
     yazılı
    -0.26
    POSITIVE LOGITS
    tvguidetime
    0.66
    WireFormatLite
    0.63
     imagui
    0.60
     dieſe
    0.60
    <unused11>
    0.57
    <unused43>
    0.57
    <unused52>
    0.57
    <unused42>
    0.57
    <unused20>
    0.57
    <unused41>
    0.57
    Act Density 0.015%

    No Known Activations