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

    Neuronpedia

    INDEX
    Explanations

    General English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    caff
    -0.07
    BMI
    -0.06
     rdr
    -0.06
    _RANK
    -0.06
     chores
    -0.06
    _ly
    -0.06
     over
    -0.06
     probl
    -0.06
    +')
    -0.06
     disple
    -0.06
    POSITIVE LOGITS
    λιο
    0.07
    _partition
    0.07
    acja
    0.06
     Animation
    0.06
    .example
    0.06
    vik
    0.06
    Pixel
    0.06
     hayvan
    0.06
     SSD
    0.06
     těch
    0.06
    Act Density 0.000%

    No Known Activations