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

    Neuronpedia

    INDEX
    Explanations

    biological molecules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lift
    -0.07
     pain
    -0.06
     substitute
    -0.06
     LTS
    -0.06
    baseline
    -0.06
     fist
    -0.06
    وي
    -0.06
    role
    -0.06
     dive
    -0.06
    턴
    -0.06
    POSITIVE LOGITS
    -terrorism
    0.07
     Unsure
    0.07
     हमल
    0.06
     มกราคม
    0.06
    طب
    0.06
     Delhi
    0.06
     ignor
    0.06
     (("
    0.06
     Uy
    0.06
    <>↵
    0.06
    Act Density 0.101%

    No Known Activations