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

    Neuronpedia

    INDEX
    Explanations

    expressions of excitement or engagement in a conversational context

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.54
    qh
    -0.38
    RenderAtEndOf
    -0.36
    toggle
    -0.35
    pulumi
    -0.35
    IZONT
    -0.33
    sdag
    -0.33
    ρίες
    -0.32
    ᅠ
    -0.32
     Kriege
    -0.32
    POSITIVE LOGITS
     Италијани
    0.62
    GEBURTSDATUM
    0.60
     المعيارى
    0.60
    OGND
    0.58
    0.57
     Exacts
    0.53
    ंदीखरीदारी
    0.52
    Parcelize
    0.50
     noDo
    0.49
    AndroidJUnit
    0.47
    Act Density 0.005%

    No Known Activations