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

    Neuronpedia

    INDEX
    Explanations

    section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     costo
    -0.07
     FRONT
    -0.07
    ISTER
    -0.06
     hs
    -0.06
    iblings
    -0.06
     atas
    -0.06
    Farm
    -0.06
    _LICENSE
    -0.06
     famille
    -0.06
     Pers
    -0.06
    POSITIVE LOGITS
     section
    0.08
     Section
    0.07
    −
    0.07
    section
    0.07
    گونه
    0.07
    jax
    0.06
    ]-
    0.06
     subsection
    0.06
     Utf
    0.06
    Section
    0.06
    Act Density 0.015%

    No Known Activations