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

    Neuronpedia

    INDEX
    Explanations

    conditional clauses

    np_max-act · gemini-2.0-flash

    The neuron selectively lights up on floating‐point number literals (decimal constants) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    orning
    -0.07
    طبي
    -0.07
    eton
    -0.06
     Guidelines
    -0.06
     иногда
    -0.06
     ।↵↵
    -0.06
    atio
    -0.06
     Core
    -0.06
    asio
    -0.06
     chiếu
    -0.06
    POSITIVE LOGITS
     Franc
    0.07
     diabetic
    0.07
     restraining
    0.06
     dword
    0.06
    _PED
    0.06
    BW
    0.06
    dag
    0.06
    very
    0.06
    Als
    0.06
    faction
    0.06
    Act Density 0.116%

    No Known Activations