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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KHR
    -0.07
     salty
    -0.07
     kní
    -0.06
    olla
    -0.06
    _NULL
    -0.06
    path
    -0.06
    تن
    -0.06
    ernaut
    -0.06
     caliente
    -0.06
    彼
    -0.06
    POSITIVE LOGITS
    variables
    0.07
     projected
    0.07
     ให
    0.07
    美
    0.06
    (withId
    0.06
    gnu
    0.06
     
    0.06
     revisit
    0.06
    ...]↵↵
    0.06
    visit
    0.06
    Act Density 0.147%

    No Known Activations