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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs related to function definitions and control flow

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

    Code snippets or code-related terms

    np_acts-logits-general · gemini-2.0-flash

    moral convictions, can be, and successor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelper
    -0.55
     sal
    -0.53
     cor
    -0.53
     fra
    -0.52
     bra
    -0.50
     dé
    -0.47
     gar
    -0.47
     reg
    -0.46
     com
    -0.44
    ensa
    -0.44
    POSITIVE LOGITS
     الحره
    0.96
     surla
    0.83
     незавершена
    0.82
    parsedMessage
    0.81
     Baillargeon
    0.81
     للاسماء
    0.81
    featureID
    0.80
     laude
    0.80
    InjectAttribute
    0.77
     дописавши
    0.77
    Act Density 0.105%

    No Known Activations