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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects type-name tokens (e.g. class or interface identifiers in CamelCase) in code and XML signatures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    อค
    -0.07
    verbatim
    -0.07
     Huff
    -0.06
    AAP
    -0.06
    Based
    -0.06
    (static
    -0.06
    �
    -0.06
    _method
    -0.06
     NSString
    -0.06
    public
    -0.06
    POSITIVE LOGITS
     �
    0.07
     glUniform
    0.07
     ПО
    0.06
     brutality
    0.06
     Madonna
    0.06
    <\/
    0.06
     เล
    0.06
    	glUniform
    0.06
     паци
    0.06
     Rece
    0.06
    Act Density 0.020%

    No Known Activations