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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash

    The neuron detects polite requests or pleas—words like “ask,” “beg,” or “please” indicating someone is requesting permission or favor.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Minimum
    -0.07
    Comments
    -0.07
     ""}↵
    -0.06
     universal
    -0.06
     сайте
    -0.06
    “How
    -0.06
    Medium
    -0.06
    diler
    -0.06
     Kotlin
    -0.06
    Rs
    -0.06
    POSITIVE LOGITS
    偶
    0.07
    (~
    0.07
    (buff
    0.06
    、
    0.06
    >(
    0.06
    .total
    0.06
    øy
    0.06
    clipboard
    0.06
    ixer
    0.06
    .import
    0.06
    Act Density 0.101%

    No Known Activations