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

    Neuronpedia

    INDEX
    Explanations

    code syntax and parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TripAdvisor
    -0.07
     Hurricanes
    -0.07
    IÓN
    -0.07
     elimination
    -0.06
    งข
    -0.06
    랑스
    -0.06
     Gibraltar
    -0.06
     Role
    -0.06
     Bel
    -0.06
     سرمایه
    -0.06
    POSITIVE LOGITS
    slide
    0.07
    lator
    0.06
    piel
    0.06
    roducing
    0.06
     aber
    0.06
    Sample
    0.06
    inha
    0.06
    Об
    0.06
    .st
    0.05
     Originally
    0.05
    Act Density 0.051%

    No Known Activations