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

    Neuronpedia

    INDEX
    Explanations

    data transmission/compression

    np_max-act · gemini-2.0-flash

    The neuron fires on technical code‐documentation terms—especially mentions of pointer “compression”/“decompression” and related API tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "]["
    -0.07
    );}↵↵
    -0.06
    _EXPECT
    -0.06
     jugar
    -0.06
    (rand
    -0.06
    Hours
    -0.06
    boost
    -0.06
    unctuation
    -0.06
     Negro
    -0.06
    знача
    -0.06
    POSITIVE LOGITS
     maximize
    0.06
    ressive
    0.06
     zástup
    0.06
     multiplying
    0.06
    ıf
    0.06
     норм
    0.06
    SIM
    0.06
     masculinity
    0.06
     放
    0.06
     обл
    0.06
    Act Density 0.373%

    No Known Activations