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

    Neuronpedia

    INDEX
    Explanations

    titles or positions of leadership

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

    head of title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URLException
    -0.45
     esporte
    -0.40
    <bos>
    -0.39
     Dox
    -0.39
    VCR
    -0.39
    áncer
    -0.37
    Algérie
    -0.36
    𝙑
    -0.36
     MOA
    -0.35
     فريبيس
    -0.35
    POSITIVE LOGITS
     Head
    0.91
    Head
    0.84
     head
    0.84
     HEAD
    0.83
    head
    0.78
     heads
    0.74
     Heads
    0.69
     leader
    0.68
     GlobalKey
    0.67
     Leiter
    0.66
    Act Density 0.007%

    No Known Activations