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

    Neuronpedia

    INDEX
    Explanations

    healthy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BSD
    -0.09
     BSD
    -0.08
     personalities
    -0.08
     hostility
    -0.08
     Nur
    -0.07
    -ee
    -0.07
     Logistics
    -0.07
    իա
    -0.07
     장애
    -0.07
    hu
    -0.07
    POSITIVE LOGITS
     recipe
    0.10
     उपाय
    0.09
    措施
    0.09
     ингреди
    0.09
     stuff
    0.09
     ingredients
    0.09
     поступ
    0.09
    recipes
    0.08
     hopp
    0.08
     substituted
    0.08
    Act Density 0.013%

    No Known Activations