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

    Neuronpedia

    INDEX
    Explanations

    lists and enumerations

    np_max-act · gemini-2.0-flash

    This neuron detects list‐introduction cues—words and phrases (e.g. "things such as," parentheses, "etc") that signal enumeration of items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    anvas
    -0.07
     Pocket
    -0.07
    -tested
    -0.06
    abbit
    -0.06
    /page
    -0.06
    avi
    -0.06
    Pocket
    -0.06
    velope
    -0.06
    ichern
    -0.06
    WM
    -0.06
    POSITIVE LOGITS
     subconscious
    0.07
     executives
    0.07
     ft
    0.07
     StartTime
    0.06
    })();
    0.06
    *math
    0.06
    Ir
    0.06
     e
    0.06
     Dw
    0.06
     остан
    0.06
    Act Density 0.008%

    No Known Activations