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

    Neuronpedia

    INDEX
    Explanations

    .jar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Con
    -0.07
    짝
    -0.07
    解放思想
    -0.07
     Judith
    -0.07
    ulner
    -0.07
    虽然是
    -0.07
    ädchen
    -0.07
    emento
    -0.07
     wielding
    -0.07
    getitem
    -0.07
    POSITIVE LOGITS
    alternative
    0.08
     orig
    0.06
    )},↵
    0.06
     Sessions
    0.06
     Fayette
    0.06
    ").↵
    0.06
     Supreme
    0.06
     destabil
    0.06
     arriv
    0.06
     .↵
    0.06
    Act Density 0.001%

    No Known Activations