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

    Neuronpedia

    INDEX
    Explanations

    distribution or scope

    np_max-act · gemini-2.0-flash

    This neuron detects numeric data or statistical/quantitative expressions in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (actor
    -0.06
     mechanism
    -0.06
     humanitarian
    -0.06
     servicing
    -0.06
     Collabor
    -0.06
     playwright
    -0.06
     misconception
    -0.06
     squeezing
    -0.06
    ANGO
    -0.06
    Professor
    -0.06
    POSITIVE LOGITS
     '{$
    0.07
     chromat
    0.07
    tti
    0.06
    ovat
    0.06
    ウト
    0.06
    gis
    0.06
    เ�
    0.06
     Hans
    0.06
     hüküm
    0.06
    ImGui
    0.06
    Act Density 0.087%

    No Known Activations