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

    Neuronpedia

    INDEX
    Explanations

    instructions and guidelines related to behavior, communication, and social etiquette

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

    Imperative verbs followed by direct objects

    np_acts-logits-general · gemini-2.0-flash

    verbs after comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.87
    UnusedPrivate
    -0.85
    GEBURTSDATUM
    -0.78
    ########.
    -0.77
     abounds
    -0.77
    OGND
    -0.75
    الحياه
    -0.73
     المعيارى
    -0.70
    ReusableCell
    -0.70
    Autoritní
    -0.69
    POSITIVE LOGITS
     don
    0.88
     make
    0.85
     feel
    0.72
     please
    0.72
     go
    0.70
     try
    0.70
     take
    0.68
     be
    0.66
     give
    0.65
     do
    0.63
    Act Density 0.157%

    No Known Activations