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

    Neuronpedia

    INDEX
    Explanations

    categorization of groups

    np_max-act · gemini-2.0-flash

    The neuron fires on terms that denote statistical grouping or classification methods—e.g. references to clusters, patterns, profiles, types, trajectories, or typologies.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ê
    -0.07
    nds
    -0.06
    (DE
    -0.06
     hour
    -0.06
    Skills
    -0.06
    ,args
    -0.06
    анні
    -0.06
     अक
    -0.06
     미
    -0.06
    CELER
    -0.06
    POSITIVE LOGITS
    lehem
    0.07
    construction
    0.07
     ジ
    0.06
     vyd
    0.06
    ]='\
    0.06
     appeared
    0.06
    .setCancelable
    0.06
    ратно
    0.06
     disput
    0.06
    esát
    0.06
    Act Density 0.040%

    No Known Activations