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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash

    classes and methods related to user interface elements in programming.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects floating‐point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     "))
    -0.07
    жения
    -0.07
    nets
    -0.07
    уму
    -0.06
    		↵
    -0.06
    -prom
    -0.06
    Compact
    -0.06
     irres
    -0.06
     ihnen
    -0.06
     sanitation
    -0.06
    POSITIVE LOGITS
     Paste
    0.07
    ?
    0.06
     Jak
    0.06
    ;r
    0.06
     FAR
    0.06
    Ｅ
    0.06
     �
    0.06
    MK
    0.06
     yaptı
    0.06
     ense
    0.06
    Act Density 0.016%

    No Known Activations