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

    Neuronpedia

    INDEX
    Explanations

    .h files

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “Util” or “Utils” identifiers (i.e. import/include references to utility classes or modules).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    सर
    -0.07
    .tags
    -0.06
     spoon
    -0.06
     Trinity
    -0.06
     nemus
    -0.06
    reur
    -0.06
     colonial
    -0.06
     Kum
    -0.06
     burdens
    -0.06
     Manila
    -0.06
    POSITIVE LOGITS
     спож
    0.07
     continuously
    0.06
    ための
    0.06
     melod
    0.06
    DbType
    0.06
     　　　
    0.06
     ص
    0.06
    dense
    0.06
    Ext
    0.06
    ічний
    0.06
    Act Density 0.014%

    No Known Activations