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

    Neuronpedia

    INDEX
    Explanations

    题

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ത്തോടെ
    -0.08
    AG
    -0.07
    طار
    -0.07
    \Config
    -0.07
    ahan
    -0.07
     saff
    -0.07
     libera
    -0.07
     Tri
    -0.07
    Advanced
    -0.07
    aktu
    -0.07
    POSITIVE LOGITS
     الشعب
    0.10
    /topic
    0.08
     vocabulary
    0.08
     огранич
    0.08
    -values
    0.08
     provinc
    0.08
    全国
    0.08
    ениями
    0.07
     imobili
    0.07
     universe
    0.07
    Act Density 0.012%

    No Known Activations