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

    Neuronpedia

    INDEX
    Explanations

    requirements, compliance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    radius
    -0.07
    agnetic
    -0.07
    τις
    -0.06
     Tecn
    -0.06
     "")↵
    -0.06
     оконч
    -0.06
     href
    -0.06
     kan
    -0.06
    .prefix
    -0.06
    459
    -0.06
    POSITIVE LOGITS
     refs
    0.07
     modifies
    0.06
    .$
    0.06
     क
    0.06
     m�
    0.06
    мин
    0.06
     fucked
    0.06
    .pre
    0.06
    ्ट
    0.06
    .test
    0.06
    Act Density 0.096%

    No Known Activations