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

    Neuronpedia

    INDEX
    Explanations

    references to specific titles and characters from fantasy and action movies

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

    "Halo" or "Hobbit" text passages

    np_acts-logits-general · gemini-2.0-flash

    dark halo model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.49
    SuspendLayout
    -0.48
     snake
    -0.41
    jda
    -0.37
     Employ
    -0.36
     habet
    -0.36
    employment
    -0.36
     fallo
    -0.35
     equi
    -0.35
    wapV
    -0.34
    POSITIVE LOGITS
    0.75
    olkien
    0.67
     Tolkien
    0.64
     Hobbit
    0.54
     Picchu
    0.53
     hobbit
    0.53
     utafitiHapana
    0.49
     rhestr
    0.47
     dictadura
    0.46
     AssemblyCulture
    0.46
    Act Density 0.250%

    No Known Activations