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

    Neuronpedia

    INDEX
    Explanations

    Dollars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ＼:
    -0.07
    itat
    -0.07
    raç
    -0.07
     yavaş
    -0.07
    těž
    -0.07
    ckså
    -0.06
     jal
    -0.06
    [keys
    -0.06
    command
    -0.06
    ตะ
    -0.06
    POSITIVE LOGITS
     motorists
    0.06
     GIR
    0.06
     notes
    0.06
    .annotations
    0.06
    include
    0.06
    midi
    0.06
     pow
    0.06
    night
    0.06
    'hui
    0.06
    .features
    0.06
    Act Density 0.013%

    No Known Activations