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

    Neuronpedia

    INDEX
    Explanations

    structured references and definitions regarding positions and classifications

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

    position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.46
     onOptions
    -0.43
    JMenu
    -0.39
    Erreferentziak
    -0.36
     mediator
    -0.35
     Pentagon
    -0.35
     agência
    -0.35
     Mediator
    -0.34
     Vainqueur
    -0.34
     agent
    -0.34
    POSITIVE LOGITS
     position
    1.45
     positions
    1.33
     Position
    1.30
    position
    1.27
    Position
    1.24
     POSITION
    1.23
     Positions
    1.20
    Positions
    1.18
    positions
    1.16
     posición
    1.09
    Act Density 0.083%

    No Known Activations