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

    Neuronpedia

    INDEX
    Explanations

    references to militant groups and their organizations

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

    group names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    postsleuth
    -0.55
     esternos
    -0.48
     nevo
    -0.45
    olescence
    -0.45
     Parkplatz
    -0.44
     المعيارى
    -0.44
    parsedMessage
    -0.43
     genomen
    -0.43
     semelh
    -0.42
    óloga
    -0.42
    POSITIVE LOGITS
     Qaeda
    0.48
    Qaeda
    0.44
     organization
    0.42
     Army
    0.42
     army
    0.41
     syndicate
    0.40
     conspiracy
    0.40
     gang
    0.40
     Organization
    0.39
     Brotherhood
    0.38
    Act Density 0.174%

    No Known Activations