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

    Neuronpedia

    INDEX
    Explanations

    hat

    np_max-act · gemini-2.0-flash

    This neuron fires on Hungarian-language words or morphemes, effectively detecting segments written in Hungarian.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     diets
    -0.07
     Swiss
    -0.06
     uninitialized
    -0.06
     gaze
    -0.06
    *K
    -0.06
     Neal
    -0.06
    Dirty
    -0.06
     proprietary
    -0.06
    avors
    -0.06
    hints
    -0.06
    POSITIVE LOGITS
    �
    0.07
    testCase
    0.07
    ophone
    0.07
    inclu
    0.06
    _UPDATE
    0.06
     renegot
    0.06
    (chunk
    0.06
    .Companion
    0.06
    규
    0.06
    	register
    0.06
    Act Density 0.055%

    No Known Activations