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

    Neuronpedia

    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Table
    -0.09
    near
    -0.07
     bà
    -0.07
     Writer
    -0.07
    Timer
    -0.07
     Taxes
    -0.07
    Actions
    -0.07
    =None
    -0.07
    .ImageIcon
    -0.07
     Controller
    -0.07
    POSITIVE LOGITS
     şi
    0.07
     stockholm
    0.06
     �
    0.06
    šli
    0.06
    -flat
    0.06
     ولكن
    0.06
    шт
    0.06
    ократи
    0.05
     kön
    0.05
    が
    0.05
    Act Density 0.009%

    No Known Activations