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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     google
    -0.07
    uropean
    -0.07
     Saved
    -0.07
     Agriculture
    -0.07
    別
    -0.07
     Global
    -0.07
    Aaron
    -0.07
     sĩ
    -0.06
    imd
    -0.06
     GT
    -0.06
    POSITIVE LOGITS
    _KEY
    0.07
    —or
    0.06
    iday
    0.06
    [property
    0.06
    [f
    0.06
     compuls
    0.06
    >()->
    0.06
    asto
    0.06
    cribed
    0.05
    oked
    0.05
    Act Density 0.004%

    No Known Activations