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

    Neuronpedia

    INDEX
    Explanations

    references to safety, security, and legal matters related to defense and law enforcement

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

    after capitalized words

    np_acts-logits-general · gemini-2.0-flash

    news headlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     approximately
    -0.77
     appunto
    -0.67
    hereinafter
    -0.67
    sequently
    -0.66
    approximately
    -0.66
    件事情
    -0.65
     subsequently
    -0.64
     aqueles
    -0.63
     consequently
    -0.63
    JvmStatic
    -0.62
    POSITIVE LOGITS
     ‘
    1.15
     '
    1.12
     govt
    0.98
    </h1>
    0.85
    ...'
    0.83
    ’:
    0.81
    ...:
    0.76
     ':
    0.75
     Govt
    0.74
    ':
    0.74
    Act Density 0.168%

    No Known Activations