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

    Neuronpedia

    INDEX
    Explanations

    phrases that express intention or future actions

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

    expressing future intent or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.59
     rodillas
    -0.44
    -0.43
    Personensuche
    -0.42
    Portale
    -0.42
    utilisons
    -0.41
    了呢
    -0.39
     salvación
    -0.39
     authenticity
    -0.38
     ExecuteAsync
    -0.38
    POSITIVE LOGITS
    gonna
    0.58
    Gonna
    0.56
     Gonna
    0.55
     gonna
    0.54
     betweenstory
    0.52
     MenuView
    0.50
     PRET
    0.48
     Aene
    0.46
     vist
    0.45
     mario
    0.45
    Act Density 0.010%

    No Known Activations