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

    Neuronpedia

    INDEX
    Explanations

    fat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    已经
    -0.07
    給
    -0.06
     unfinished
    -0.06
     ages
    -0.06
     offseason
    -0.06
    damage
    -0.06
    _feed
    -0.06
    .camera
    -0.06
    (sum
    -0.06
     Avalanche
    -0.06
    POSITIVE LOGITS
     handlers
    0.07
     VARIABLES
    0.07
    тоф
    0.07
     ritual
    0.07
     container
    0.07
    τό
    0.07
     katı
    0.07
    ils
    0.06
    ill
    0.06
     sponsors
    0.06
    Act Density 0.002%

    No Known Activations