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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    porte
    -0.07
    ену
    -0.07
     стандарт
    -0.06
     populated
    -0.06
     crawled
    -0.06
    _zeros
    -0.06
    quick
    -0.06
     sourcing
    -0.06
    ISIBLE
    -0.06
     cashier
    -0.06
    POSITIVE LOGITS
     Astro
    0.06
    JEXEC
    0.06
    ODO
    0.06
     prohibit
    0.06
    ologne
    0.06
     conceptual
    0.06
     расс
    0.06
    UPER
    0.06
    ینگ
    0.05
     прави
    0.05
    Act Density 0.040%

    No Known Activations