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

    Neuronpedia

    INDEX
    Explanations

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RSA
    -0.08
    _flag
    -0.08
    aleza
    -0.07
    ases
    -0.07
     assumes
    -0.06
    aur
    -0.06
    “And
    -0.06
    ¨¨
    -0.06
     Mour
    -0.06
     제공
    -0.06
    POSITIVE LOGITS
     top
    0.17
     Top
    0.13
    Top
    0.12
     TOP
    0.11
    -top
    0.09
    .Top
    0.08
    	top
    0.08
     Laptop
    0.07
     pinpoint
    0.07
    (top
    0.07
    Act Density 0.011%

    No Known Activations