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

    Neuronpedia

    INDEX
    Explanations

    references to military or warfare-related themes

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

    invasion and outnumbered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eş
    -0.37
     seules
    -0.36
     christlichen
    -0.36
     bandoulière
    -0.35
     obdob
    -0.34
     ativos
    -0.34
     azules
    -0.33
     venuto
    -0.33
     esposa
    -0.33
     alça
    -0.33
    POSITIVE LOGITS
    Invasion
    0.66
     horde
    0.65
    invasion
    0.65
     Invasion
    0.63
     invasion
    0.63
     swarm
    0.60
     legion
    0.59
     hordes
    0.58
    scriptId
    0.57
     ویکی‌پدی
    0.56
    Act Density 0.173%

    No Known Activations