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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     in
    -0.10
     on
    -0.09
     On
    -0.09
     into
    -0.09
    On
    -0.09
     IN
    -0.09
     In
    -0.08
     To
    -0.08
    In
    -0.08
     ON
    -0.08
    POSITIVE LOGITS
    <d
    0.07
    restaurant
    0.06
    σταση
    0.06
    (process
    0.06
     simil
    0.06
    є
    0.06
     Pornhub
    0.06
     받아
    0.06
    uib
    0.06
    -transitional
    0.06
    Act Density 0.415%

    No Known Activations