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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals containing decimal points (i.e. floating‐point constants).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    іх
    -0.07
    ст
    -0.07
     Ir
    -0.06
     TAR
    -0.06
    ことは
    -0.06
    <()>
    -0.06
     provocative
    -0.06
    ัน
    -0.06
     SAN
    -0.06
     scheduler
    -0.06
    POSITIVE LOGITS
     MAIN
    0.07
    (contents
    0.07
    ]^
    0.07
     nhắc
    0.06
     disag
    0.06
    -basket
    0.06
    -target
    0.06
     CharSet
    0.06
    '>";↵
    0.06
     žal
    0.06
    Act Density 0.007%

    No Known Activations