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

    Neuronpedia

    INDEX
    Explanations

    Table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acidic
    -0.07
     banned
    -0.07
    ','.
    -0.06
    .Address
    -0.06
    Managing
    -0.06
     ################################################
    -0.06
    ypical
    -0.06
     identify
    -0.06
     '-'
    -0.06
    ("",
    -0.06
    POSITIVE LOGITS
    μως
    0.07
    방
    0.07
    (hex
    0.07
     función
    0.06
     регули
    0.06
    /list
    0.06
     searchData
    0.06
     režim
    0.06
     Pornhub
    0.06
     возможность
    0.06
    Act Density 0.034%

    No Known Activations