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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intersection
    -0.07
     说
    -0.07
    -spacing
    -0.06
     dl
    -0.06
    ,the
    -0.06
    "Our
    -0.06
    已经
    -0.06
    说
    -0.06
     STEP
    -0.06
     аналіз
    -0.06
    POSITIVE LOGITS
    angu
    0.07
    (cf
    0.06
     Supervisor
    0.06
    Unload
    0.06
    ُ
    0.06
     Tyto
    0.06
     BindingFlags
    0.06
     gang
    0.06
    Escort
    0.06
     intox
    0.06
    Act Density 0.008%

    No Known Activations