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

    Neuronpedia

    INDEX
    Explanations

    evidence or indicators of potential changes or conditions in various contexts

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

    transition words introducing new information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.48
    aarrggbb
    -0.44
    PreferredItem
    -0.43
    AdapterFactory
    -0.42
    astéro
    -0.42
     przecież
    -0.41
     pinulongan
    -0.41
    >{@
    -0.41
     Überg
    -0.40
     BoxDecoration
    -0.39
    POSITIVE LOGITS
    BeginInit
    0.43
    loyed
    0.42
    MergeFrom
    0.41
    ImageContext
    0.40
    Rhestr
    0.39
    ſelf
    0.39
    ьев
    0.39
    EndContext
    0.38
     snippetHide
    0.38
    RTCK
    0.38
    Act Density 0.024%

    No Known Activations