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

    Neuronpedia

    INDEX
    Explanations

    32

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    206
    -0.08
    oy
    -0.08
    (ship
    -0.07
     admired
    -0.07
     Dare
    -0.07
    ості
    -0.07
    "..
    -0.07
    ('--
    -0.07
    '''↵
    -0.07
     Sob
    -0.06
    POSITIVE LOGITS
    -cluster
    0.07
    CELL
    0.07
    ارک
    0.07
    CALE
    0.07
    cls
    0.07
     LCD
    0.07
     electrónico
    0.07
    pack
    0.07
    32
    0.07
    く
    0.06
    Act Density 0.010%

    No Known Activations