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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wright
    -0.07
    éné
    -0.06
     epilepsy
    -0.06
     migrated
    -0.06
    _freq
    -0.06
     consumption
    -0.06
     wann
    -0.06
     helpless
    -0.06
     struck
    -0.06
     side
    -0.06
    POSITIVE LOGITS
     Univ
    0.07
    Austin
    0.07
     bun
    0.06
    ctx
    0.06
     debacle
    0.06
     gluten
    0.06
    Tho
    0.06
    █
    0.06
     Sofia
    0.06
     kuş
    0.06
    Act Density 0.085%

    No Known Activations