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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash

    The neuron is triggered by occurrences of the “.” separator in code (e.g. the dot operator in package/import/class names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ele
    -0.07
    CppI
    -0.06
     Bazı
    -0.06
    SKU
    -0.06
     dnů
    -0.06
     minValue
    -0.06
    @Getter
    -0.06
    문을
    -0.06
    	Date
    -0.06
     butto
    -0.06
    POSITIVE LOGITS
     SLOT
    0.07
     casts
    0.06
     акт
    0.06
     AR
    0.06
     relationship
    0.06
     ITER
    0.06
     crimes
    0.06
     Processing
    0.06
    ductor
    0.06
     bidi
    0.06
    Act Density 0.001%

    No Known Activations