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

    Neuronpedia

    INDEX
    Explanations

    concepts related to ideology, power dynamics, and societal structures

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

    followed by question marks or contractions

    np_acts-logits-general · gemini-2.0-flash

    election outcomes evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]='\
    -0.68
    δας
    -0.55
    ')}}"
    -0.53
    而是
    -0.52
    ANGAN
    -0.49
    ⓘ
    -0.48
    ">${
    -0.48
    OTES
    -0.48
    页面存档备份
    -0.47
    يكب
    -0.46
    POSITIVE LOGITS
     shouldn
    1.46
     certainly
    1.38
     isn
    1.36
     needn
    1.29
     doesn
    1.25
     wasn
    1.22
     didn
    1.21
     wouldn
    1.16
     ain
    1.15
    ?
    1.15
    Act Density 0.653%

    No Known Activations