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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures, particularly focusing on their lineage or titles

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

    bin or ibn or Mac followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.52
    expandindo
    -0.39
    ReusableCell
    -0.37
     ſta
    -0.36
     referrerpolicy
    -0.35
    foglal
    -0.35
     ſtate
    -0.34
    Etc
    -0.34
     collectively
    -0.34
     bonté
    -0.33
    POSITIVE LOGITS
     bin
    0.94
     ibn
    0.85
     Bin
    0.83
     Ibn
    0.79
     ابن
    0.75
     BIN
    0.74
    Ibn
    0.74
     bint
    0.72
    Bin
    0.71
     بن
    0.66
    Act Density 0.012%

    No Known Activations