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

    Neuronpedia

    INDEX
    Explanations

    difficult journey ahead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     آل
    -0.07
    แนว
    -0.07
     pohod
    -0.07
    irl
    -0.07
     Cy
    -0.07
     Mort
    -0.07
    нед
    -0.06
     Por
    -0.06
     Met
    -0.06
    Carol
    -0.06
    POSITIVE LOGITS
    당
    0.06
     reflecting
    0.06
     confirming
    0.06
    ์ก
    0.06
     ש
    0.06
    -account
    0.06
    have
    0.06
     فرهنگی
    0.06
     reflected
    0.06
     посад
    0.06
    Act Density 0.007%

    No Known Activations