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

    Neuronpedia

    INDEX
    Explanations

    references to specific models or systems and their characteristics

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

    systems and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    colnshire
    -0.44
    mouseout
    -0.38
    ventude
    -0.38
    baguna
    -0.38
    DeleteCommand
    -0.37
    nerability
    -0.37
    xiety
    -0.36
    easter
    -0.35
    indrops
    -0.35
    PLIANCE
    -0.35
    POSITIVE LOGITS
     arrangement
    0.69
     arrangements
    0.65
     Arrangement
    0.57
     informée
    0.57
     arrange
    0.56
     modalidad
    0.56
    ValueStyle
    0.55
     arranges
    0.53
     Arrangements
    0.52
     arrang
    0.49
    Act Density 0.119%

    No Known Activations