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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of open-source and openness

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

    open, communication, source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.59
    MessageTagHelper
    -0.58
    Autoritní
    -0.56
     CreateTagHelper
    -0.51
    inSlope
    -0.49
    amental
    -0.49
    inerary
    -0.49
    campal
    -0.49
    quelize
    -0.48
     DataTypes
    -0.48
    POSITIVE LOGITS
     openness
    0.69
     open
    0.58
     abiertas
    0.56
     abierta
    0.53
     abierto
    0.51
     openly
    0.50
     Open
    0.49
     abiertos
    0.48
     terbuka
    0.48
     öppna
    0.48
    Act Density 0.012%

    No Known Activations