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

    Neuronpedia

    INDEX
    Explanations

    tos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     date
    -0.08
     words
    -0.07
    Oper
    -0.07
    date
    -0.07
     were
    -0.07
     link
    -0.07
    Net
    -0.06
     coke
    -0.06
     veri
    -0.06
     Ryan
    -0.06
    POSITIVE LOGITS
     انگ
    0.07
     inclination
    0.07
    olean
    0.07
    ulating
    0.06
     stockholm
    0.06
    930
    0.06
    葡
    0.06
    etically
    0.06
    าช
    0.06
     "'.
    0.06
    Act Density 0.086%

    No Known Activations