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

    Neuronpedia

    INDEX
    Explanations

    references to battles and conflicts

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

    Precedes words relating to conflict/war

    np_acts-logits-general · gemini-2.0-flash

    battle followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    -0.94
    ness
    -0.88
     ***!
    -0.84
    ers
    -0.82
    ING
    -0.67
    ים
    -0.66
    ning
    -0.66
    est
    -0.63
    asthan
    -0.63
    으로
    -0.62
    POSITIVE LOGITS
    routeProvider
    0.81
    tonsoft
    0.79
     ―――――
    0.75
     }}"></
    0.74
     ――――――――
    0.70
    tle
    0.69
    e
    0.69
    tti
    0.68
    ization
    0.67
    mente
    0.67
    Act Density 0.285%

    No Known Activations