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

    Neuronpedia

    INDEX
    Explanations

    instances of settings, configurations, and behavior customizations in technical contexts

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

    preventing or stopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.46
    PullParser
    -0.45
    parsedMessage
    -0.44
    liferay
    -0.40
     autorytatywna
    -0.40
     Chwiliwch
    -0.40
     Signalez
    -0.39
    BagConstraints
    -0.39
    tonsoft
    -0.39
    icksburg
    -0.38
    POSITIVE LOGITS
    verwijspagina
    0.48
     disgraceful
    0.43
     annoying
    0.43
     horrible
    0.41
     ControllerBase
    0.41
     wierd
    0.41
     Menace
    0.40
     Ibra
    0.40
    SerializedName
    0.40
    clientID
    0.39
    Act Density 0.073%

    No Known Activations