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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Represent
    -0.07
    consider
    -0.06
    _INCREMENT
    -0.06
    IFO
    -0.06
     Interpret
    -0.06
     mau
    -0.06
    Wiki
    -0.06
    Blo
    -0.06
     WAR
    -0.06
     viable
    -0.06
    POSITIVE LOGITS
     dessa
    0.07
    ัส
    0.07
     manufacturers
    0.07
     küt
    0.07
     dust
    0.07
     "../../../../
    0.07
    清
    0.07
    하게
    0.06
    自分の
    0.06
     Jesus
    0.06
    Act Density 0.017%

    No Known Activations