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

    Neuronpedia

    INDEX
    Explanations

    sagt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wizards
    -0.06
     Воз
    -0.06
     Annex
    -0.06
     Emirates
    -0.06
     recl
    -0.06
     Brad
    -0.06
    record
    -0.06
     Typically
    -0.06
    aturday
    -0.06
     cường
    -0.06
    POSITIVE LOGITS
     sagt
    0.17
     sagen
    0.14
     sagte
    0.12
     Saga
    0.09
     Savage
    0.09
    agen
    0.09
    Saga
    0.08
     сказать
    0.08
     saga
    0.08
     sujet
    0.07
    Act Density 0.006%

    No Known Activations