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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to requests, participation, and support

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

    verbs followed by specific prepositions or articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.68
     ſind
    -0.65
     unſ
    -0.61
    parsedMessage
    -0.61
    iffance
    -0.61
     Meksiku
    -0.60
     surla
    -0.60
     パンチラ
    -0.60
     imagui
    -0.60
     iſt
    -0.60
    POSITIVE LOGITS
     ולה
    0.33
     jangan
    0.31
     aumentado
    0.31
     cardiaque
    0.30
    IntoConstraints
    0.30
     externi
    0.30
     chảy
    0.29
     mejorado
    0.29
     their
    0.29
     prohibido
    0.28
    Act Density 0.059%

    No Known Activations