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

    Neuronpedia

    INDEX
    Explanations

    references to actions and their impacts in a narrative context

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

    pays off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desconocido
    -0.40
     Paglinawan
    -0.36
     wiedzieć
    -0.36
     ángeles
    -0.35
     ulasan
    -0.35
     ibunya
    -0.35
     jongen
    -0.34
     fotografico
    -0.34
     rodzic
    -0.34
     myśli
    -0.34
    POSITIVE LOGITS
     ProtoMessage
    0.59
     autorytatywna
    0.58
    webElementXpaths
    0.57
     reflected
    0.54
     iprot
    0.53
    ThroughAttribute
    0.53
    onActivityResult
    0.52
    recated
    0.52
     invokingState
    0.50
    Сылтамалар
    0.50
    Act Density 0.112%

    No Known Activations