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

    Neuronpedia

    INDEX
    Explanations

    Math computations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Floyd
    -0.06
     Pony
    -0.06
     Ninh
    -0.06
     Emoji
    -0.06
    º
    -0.06
     없어
    -0.06
     laughing
    -0.06
     Diagram
    -0.06
    Elizabeth
    -0.06
     rented
    -0.06
    POSITIVE LOGITS
    aston
    0.06
    ніст
    0.06
     το
    0.06
    anguard
    0.06
    _iterations
    0.06
    ニ
    0.06
    .v
    0.06
    .weapon
    0.06
     mag
    0.06
    =edge
    0.06
    Act Density 0.016%

    No Known Activations