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

    Neuronpedia

    INDEX
    Explanations

    words related to accidents or damage involving vehicles

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

    wreck and its forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tableFuture
    -0.71
    AndEndTag
    -0.61
     Antara
    -0.59
     Tania
    -0.59
     المعيارى
    -0.59
     Bondi
    -0.59
     صوتيه
    -0.59
    bondale
    -0.59
     Alina
    -0.59
     LDA
    -0.59
    POSITIVE LOGITS
     wreck
    1.77
    wreck
    1.65
     Wreck
    1.53
     wrecks
    1.46
     wrecking
    1.35
     wrecked
    1.32
     Wre
    1.23
    wre
    1.23
    Wre
    1.21
     wreckage
    1.18
    Act Density 0.003%

    No Known Activations