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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    The neuron is chiefly activated by numeric tokens (including integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Dao
    -0.07
     болезни
    -0.07
     خاک
    -0.06
     곧
    -0.06
    animate
    -0.06
     güney
    -0.06
    simd
    -0.06
    راه
    -0.06
    YouTube
    -0.06
     alleviate
    -0.06
    POSITIVE LOGITS
    _SAMPLES
    0.07
     lange
    0.06
    .plist
    0.06
    ,text
    0.06
     PARK
    0.06
    totals
    0.06
    (descriptor
    0.06
    (',')↵
    0.06
    .java
    0.06
    Publication
    0.06
    Act Density 0.001%

    No Known Activations