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

    Neuronpedia

    INDEX
    Explanations

    Sim

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OFF
    -0.09
     collecting
    -0.08
    攻击
    -0.07
    腿部
    -0.07
    买东西
    -0.07
    ouch
    -0.07
    西甲
    -0.07
    arty
    -0.07
    奇特
    -0.07
    adata
    -0.07
    POSITIVE LOGITS
     SIM
    0.09
    агент
    0.08
    sim
    0.07
     compiler
    0.07
    ₌
    0.07
     simulator
    0.07
     simmer
    0.07
    혔
    0.07
     Sim
    0.07
     dias
    0.07
    Act Density 0.026%

    No Known Activations