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

    Neuronpedia

    INDEX
    Explanations

    government organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tours
    -0.07
     contact
    -0.06
     Phones
    -0.06
     games
    -0.06
     coup
    -0.06
    登
    -0.06
    SIGN
    -0.06
     taps
    -0.06
    ARGER
    -0.06
    tv
    -0.06
    POSITIVE LOGITS
    [line
    0.07
     confession
    0.07
    .Enable
    0.06
     Slee
    0.06
     skoro
    0.06
    โปร
    0.06
     abych
    0.06
     NSLocalizedString
    0.06
    ीश
    0.06
    [value
    0.06
    Act Density 0.087%

    No Known Activations