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

    Neuronpedia

    INDEX
    Explanations

    name changes

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of name‐change events (e.g., “changed,” “renamed,” “name”) in document histories.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    имости
    -0.07
    ah
    -0.07
     Nob
    -0.06
     IMPORT
    -0.06
     trivial
    -0.06
     싱글
    -0.06
    ीं
    -0.06
     Increment
    -0.06
     EST
    -0.06
     treasure
    -0.06
    POSITIVE LOGITS
    ظˆ
    0.07
    _Pods
    0.07
     PIXI
    0.07
    dyn
    0.06
     comma
    0.06
    ，由
    0.06
    Clazz
    0.06
    DMIN
    0.06
     duygu
    0.06
    inth
    0.06
    Act Density 0.022%

    No Known Activations