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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compact
    -0.09
     اختی
    -0.07
    	texture
    -0.06
     زی
    -0.06
     targeting
    -0.06
     вла
    -0.06
     acids
    -0.06
     singular
    -0.06
     fam
    -0.06
     rebut
    -0.06
    POSITIVE LOGITS
     jour
    0.07
    Clear
    0.06
     Carey
    0.06
    nox
    0.06
    .didReceiveMemoryWarning
    0.06
     Dem
    0.06
    Grand
    0.06
    Snap
    0.06
    Ạ
    0.06
    /modal
    0.06
    Act Density 0.024%

    No Known Activations