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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    哪些
    -0.07
    ▘
    -0.07
    知乎
    -0.07
    StateChanged
    -0.07
    igidbody
    -0.07
    ridge
    -0.07
     Sith
    -0.07
    .rar
    -0.07
    /random
    -0.07
     Angry
    -0.06
    POSITIVE LOGITS
    主持召开
    0.07
     asc
    0.07
     dcc
    0.07
    Med
    0.07
    .performance
    0.07
    care
    0.06
     Ваш
    0.06
    udence
    0.06
    ++↵
    0.06
     kc
    0.06
    Act Density 0.020%

    No Known Activations