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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    那里
    -0.07
     pudding
    -0.06
     (>
    -0.06
     Batman
    -0.06
    elves
    -0.06
    274
    -0.06
     decreased
    -0.06
     مما
    -0.06
     약
    -0.06
     då
    -0.06
    POSITIVE LOGITS
     hypert
    0.07
    resher
    0.07
     Indust
    0.07
    bral
    0.06
     shoreline
    0.06
    ilit
    0.06
    Paused
    0.06
    nd
    0.06
    泽
    0.06
     英语
    0.06
    Act Density 0.055%

    No Known Activations