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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron responds to object method calls—that is, tokens representing “.methodName” invocation patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mush
    -0.07
    
    -0.07
    polation
    -0.07
     VLAN
    -0.07
    ployment
    -0.06
    olves
    -0.06
     пош
    -0.06
    prestashop
    -0.06
    ROLE
    -0.06
    елю
    -0.06
    POSITIVE LOGITS
     refugee
    0.07
     mooie
    0.06
    jak
    0.06
    isses
    0.06
     světě
    0.06
    	reg
    0.06
     Ball
    0.06
    athan
    0.06
     đài
    0.06
     Nhà
    0.06
    Act Density 0.149%

    No Known Activations