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

    Neuronpedia

    INDEX
    Explanations

    Excerpts from writings

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens—especially floating‐point numbers and other numeric values—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     от
    -0.06
     voter
    -0.06
     임
    -0.06
    -shift
    -0.06
    ired
    -0.06
     ソ
    -0.06
    icon
    -0.06
    .VisualBasic
    -0.06
    oord
    -0.06
     送
    -0.06
    POSITIVE LOGITS
    Overview
    0.07
     COURT
    0.07
    May
    0.06
     ['',
    0.06
     �
    0.06
    nické
    0.06
     acknowledges
    0.06
    __:
    0.06
    (be
    0.06
    ----
    0.06
    Act Density 0.324%

    No Known Activations