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

    Neuronpedia

    INDEX
    Explanations

    limitations of methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Identity
    -0.07
    hibited
    -0.07
    ehicles
    -0.06
    (gs
    -0.06
    riculum
    -0.06
    れば
    -0.06
    /portfolio
    -0.06
     була
    -0.06
     münchen
    -0.06
    Politics
    -0.06
    POSITIVE LOGITS
    remaining
    0.07
     afr
    0.07
     vastly
    0.06
     rumor
    0.06
     fav
    0.06
     thẻ
    0.06
     आप
    0.06
     кот
    0.06
     меч
    0.06
     cort
    0.06
    Act Density 0.068%

    No Known Activations