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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    This neuron flags spans of text written in LaTeX‐style mathematical notation (e.g. $$…$$, \frac, \left/ \right, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ）。
    -0.07
    nard
    -0.07
     和
    -0.07
    	dd
    -0.06
     keep
    -0.06
     Hen
    -0.06
    kop
    -0.06
     hypertension
    -0.06
    ople
    -0.06
     tra
    -0.06
    POSITIVE LOGITS
    วงศ
    0.07
    iros
    0.06
    irma
    0.06
     UClass
    0.06
     verb
    0.06
    Elizabeth
    0.06
     Webcam
    0.06
    uddled
    0.06
     başlayan
    0.06
     mí
    0.06
    Act Density 0.017%

    No Known Activations