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

    Neuronpedia

    INDEX
    Explanations

    Forum/comment text

    np_max-act · gemini-2.0-flash

    The neuron fires on the first word of a new sentence or segment, i.e. tokens that begin sentences or lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _words
    -0.07
    arker
    -0.07
    �
    -0.07
     Arabic
    -0.06
     NAMES
    -0.06
    Dependencies
    -0.06
    adata
    -0.06
     Honey
    -0.06
    -sp
    -0.06
     терап
    -0.06
    POSITIVE LOGITS
    ožná
    0.08
    .isBlank
    0.07
     RecognitionException
    0.06
    mrt
    0.06
     alıyor
    0.06
     UnityEngine
    0.06
    NON
    0.06
     Hedge
    0.06
     هوش
    0.06
    @register
    0.06
    Act Density 0.090%

    No Known Activations