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

    Neuronpedia

    INDEX
    Explanations

    :ss

    np_max-act · gemini-2.0-flash

    This neuron detects time‐format specifiers (e.g. “hh”, “mm”, “ss”) in code strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Engineering
    -0.07
    ुग
    -0.06
     placements
    -0.06
     tends
    -0.06
     merkez
    -0.06
     Promotion
    -0.06
    Hen
    -0.06
     noci
    -0.06
    region
    -0.06
     Kak
    -0.06
    POSITIVE LOGITS
    /Product
    0.07
                              ↵
    0.07
    }`);↵↵
    0.06
     Encyclopedia
    0.06
                         ↵
    0.06
    Companies
    0.06
                               ↵
    0.06
    _________________↵↵
    0.06
                                ↵
    0.06
     autogenerated
    0.06
    Act Density 0.003%

    No Known Activations