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

    Neuronpedia

    INDEX
    Explanations

    political/news articles

    np_max-act · gemini-2.0-flash

    The neuron flags hypothetical “if…then” conditional statements describing how something could be improved.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     seats
    -0.07
    串
    -0.07
    .Selection
    -0.06
    (cc
    -0.06
    CMS
    -0.06
     Selector
    -0.06
     ZIP
    -0.06
     Seats
    -0.06
     mask
    -0.06
    	c
    -0.06
    POSITIVE LOGITS
     griev
    0.07
     этой
    0.06
    ERVED
    0.06
     میان
    0.06
     Nisan
    0.06
     nejd
    0.06
    �
    0.06
     facial
    0.06
    .require
    0.06
     haut
    0.06
    Act Density 0.325%

    No Known Activations