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

    Neuronpedia

    INDEX
    Explanations

    commas and dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffiti
    -0.07
     INC
    -0.07
    .master
    -0.06
    defgroup
    -0.06
     VLC
    -0.06
    zing
    -0.06
    Eric
    -0.06
    NH
    -0.06
    епти
    -0.06
     Gren
    -0.06
    POSITIVE LOGITS
     screenplay
    0.07
     करक
    0.07
    ởi
    0.06
     resolver
    0.06
    令
    0.06
     board
    0.06
    imální
    0.06
    (problem
    0.06
    _plain
    0.06
     Cly
    0.06
    Act Density 0.007%

    No Known Activations