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

    Neuronpedia

    INDEX
    Explanations

    terms related to aggressive animal behavior or confrontations

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

    ramming and charging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Похо
    -0.34
     apost
    -0.33
     '\\;'
    -0.31
    enschaften
    -0.31
     already
    -0.31
     abstin
    -0.30
    虚
    -0.30
     mér
    -0.30
     strings
    -0.30
    jordan
    -0.30
    POSITIVE LOGITS
     ویکی‌پدی
    0.71
    ьаж
    0.57
    })->
    0.56
     propOrder
    0.56
    期刊论文
    0.56
     дописавши
    0.55
     beginnetje
    0.54
    InjectAttribute
    0.54
     <>",
    0.54
     frontale
    0.52
    Act Density 0.152%

    No Known Activations