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

    Neuronpedia

    INDEX
    Explanations

    repeat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comp
    -0.08
    oban
    -0.07
     ਵਿ�
    -0.07
     ਕੰ
    -0.07
     just
    -0.07
     Cada
    -0.07
    .ga
    -0.07
    otropic
    -0.07
    Expo
    -0.07
    kom
    -0.07
    POSITIVE LOGITS
    -',
    0.08
     blandt
    0.08
     রয়েছে
    0.08
    明星
    0.08
    -",
    0.08
     स्टार
    0.08
     রয়েছে
    0.08
    ণের
    0.07
    лардың
    0.07
     актер
    0.07
    Act Density 0.016%

    No Known Activations