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

    Neuronpedia

    INDEX
    Explanations

    Chemical reactions

    np_max-act · gemini-2.0-flash

    This neuron responds to the numeric components (digits and associated hyphens) used in chemical compound names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     м
    -0.08
    ,type
    -0.07
    cancelled
    -0.06
     concent
    -0.06
    .cod
    -0.06
     narration
    -0.06
    AlgorithmException
    -0.06
    datetime
    -0.06
    GORITHM
    -0.06
    %↵
    -0.06
    POSITIVE LOGITS
     ―
    0.07
    amily
    0.06
    ilters
    0.06
     СРСР
    0.06
     vå
    0.06
    �
    0.06
    努力
    0.06
    σσα
    0.06
    بل
    0.06
     cleans
    0.06
    Act Density 0.035%

    No Known Activations