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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fragmentation
    -0.06
    960
    -0.06
    بود
    -0.06
    彻
    -0.06
    <Document
    -0.06
     Ky
    -0.05
    xC
    -0.05
     FR
    -0.05
     Bowman
    -0.05
     setter
    -0.05
    POSITIVE LOGITS
    	emit
    0.07
    ětš
    0.07
     genau
    0.07
    =[]
    0.06
    ()):
    0.06
    #a
    0.06
     endeavors
    0.06
    "]:
    0.06
    materials
    0.06
    È
    0.06
    Act Density 0.000%

    No Known Activations