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

    Neuronpedia

    INDEX
    Explanations

    elements or terminologies related to software and system configurations

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

    approving terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.71
     Infórmanos
    -0.68
    Diweddarwch
    -0.67
     InputDecoration
    -0.66
     snippetHide
    -0.64
    OGND
    -0.61
     deſſen
    -0.61
    parsedMessage
    -0.60
    見た
    -0.59
     ddelweddau
    -0.59
    POSITIVE LOGITS
     föres
    0.43
    ing
    0.42
    aktery
    0.39
    Aggi
    0.37
     recons
    0.36
    rboles
    0.35
     îng
    0.35
    ed
    0.35
    udp
    0.35
     arvio
    0.35
    Act Density 1.643%

    No Known Activations