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

    Neuronpedia

    INDEX
    Explanations

    concepts related to relationships and interactions in various contexts

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

    states with others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.59
    DockStyle
    -0.55
     فريبيس
    -0.54
     AssemblyCulture
    -0.53
     estekak
    -0.52
     ligiloj
    -0.50
     otomatig
    -0.50
    MessageOf
    -0.49
    AxisAlignment
    -0.48
    RTLD
    -0.48
    POSITIVE LOGITS
     limbo
    0.57
     mode
    0.56
     again
    0.46
     position
    0.45
    mode
    0.45
    状態
    0.42
     Mode
    0.42
     orbit
    0.40
    狀態
    0.40
    again
    0.39
    Act Density 0.104%

    No Known Activations