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

    Neuronpedia

    INDEX
    Explanations

    emotional dialogues and expressions of surprise or excitement

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

    Exclamations or interjections

    np_acts-logits-general · gemini-2.0-flash

    exclamations and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ganu
    -0.60
     defaultstate
    -0.57
    AddRange
    -0.55
    -0.55
    zepam
    -0.49
     سكانية
    -0.47
     Ultimately
    -0.46
    returnValue
    -0.46
    setAccessible
    -0.46
    Ultimately
    -0.46
    POSITIVE LOGITS
    ыгана
    0.62
     CWE
    0.60
    XmlAccessType
    0.60
    adaptiveStyles
    0.58
    Tikang
    0.56
     esternos
    0.55
     cursed
    0.54
    السكان
    0.54
     userSchema
    0.54
    กำลัง
    0.54
    Act Density 0.123%

    No Known Activations