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

    Neuronpedia

    INDEX
    Explanations

    terms related to military or siege actions

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

    siege and blockade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bailarina
    -0.43
    ambut
    -0.42
     muchacho
    -0.41
     marrone
    -0.41
    intenant
    -0.41
    eradish
    -0.40
     zgod
    -0.40
     corriger
    -0.40
     réalisation
    -0.39
     appreci
    -0.39
    POSITIVE LOGITS
     siege
    1.17
     Siege
    1.02
     besieged
    0.91
    Siege
    0.90
     besie
    0.84
     blockade
    0.63
    upol
    0.61
    blurRadius
    0.54
    HostException
    0.53
     heapq
    0.52
    Act Density 0.052%

    No Known Activations