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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     joking
    -0.07
     milling
    -0.07
    -standard
    -0.07
    204
    -0.06
    .highlight
    -0.06
    Want
    -0.06
    制造
    -0.06
    .ly
    -0.06
     Narr
    -0.06
     해야
    -0.06
    POSITIVE LOGITS
    σκ
    0.07
     STATIC
    0.07
     murderer
    0.06
    ethyl
    0.06
    SDL
    0.06
     queryInterface
    0.06
    Velocity
    0.06
     blatantly
    0.06
    ple
    0.06
    size
    0.06
    Act Density 0.002%

    No Known Activations