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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    letters
    -0.08
    fight
    -0.07
    isode
    -0.07
    ViewPager
    -0.07
    SignUp
    -0.07
    Bet
    -0.07
    Expert
    -0.07
    IFF
    -0.06
    JO
    -0.06
    ốn
    -0.06
    POSITIVE LOGITS
     birçok
    0.07
    grey
    0.07
    (Runtime
    0.07
     pytest
    0.07
    百余
    0.07
     rm
    0.07
    .displayName
    0.07
     мира
    0.07
    全县
    0.07
    ","
    0.07
    Act Density 0.060%

    No Known Activations