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

    Neuronpedia

    INDEX
    Explanations

    ист

    np_max-act · gemini-2.0-flash

    The neuron fires on Ukrainian verb forms of “to use” (e.g. various inflections of “використовувати”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Commissioners
    -0.07
    小学
    -0.07
    .MiddleLeft
    -0.06
    .setCode
    -0.06
    Distribution
    -0.06
     fish
    -0.06
    438
    -0.06
    	load
    -0.06
    -0.06
    Modes
    -0.06
    POSITIVE LOGITS
     used
    0.10
     use
    0.10
     použit
    0.09
     using
    0.08
     Used
    0.08
    wendung
    0.08
     utilized
    0.07
     acceptable
    0.07
     사용
    0.07
     använd
    0.07
    Act Density 0.053%

    No Known Activations