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

    Neuronpedia

    INDEX
    Explanations

    instances of speech or quotations

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

    speaking or communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.69
    rungsseite
    -0.68
     cauſe
    -0.52
     leſs
    -0.52
     ſtand
    -0.50
     reaſon
    -0.49
    Chham
    -0.49
     neceſſ
    -0.48
     InputDecoration
    -0.47
    itinéraire
    -0.46
    POSITIVE LOGITS
    Jereo
    0.40
     SPEECH
    0.35
    flashdata
    0.35
    Personendaten
    0.35
    PathParam
    0.33
    TWITTER
    0.33
     Speaks
    0.32
    twitter
    0.32
    Enllaces
    0.32
     آر
    0.32
    Act Density 0.096%

    No Known Activations