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

    Neuronpedia

    INDEX
    Explanations

    problems occurring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BYTE
    -0.09
    Hip
    -0.08
     grinding
    -0.08
     Grind
    -0.08
     hydrochlor
    -0.07
    HAM
    -0.07
    Grinding
    -0.07
    Esp
    -0.07
    _REMOVE
    -0.07
    Retention
    -0.07
    POSITIVE LOGITS
     noticia
    0.08
    promo
    0.08
     ഉയര്
    0.08
     bisa
    0.08
    film
    0.08
     দীর্ঘ
    0.08
     തോ
    0.07
     יכולים
    0.07
     orchestr
    0.07
     nämä
    0.07
    Act Density 0.001%

    No Known Activations