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

    Neuronpedia

    INDEX
    Explanations

    holder

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    传奇游戏
    -0.07
    就应该
    -0.06
     license
    -0.06
    可行性
    -0.06
    _equ
    -0.06
     Phạm
    -0.06
    锽
    -0.06
    ificates
    -0.06
    engage
    -0.06
    IDE
    -0.06
    POSITIVE LOGITS
    recipient
    0.07
     marrow
    0.07
    簌
    0.07
    ournemouth
    0.07
    orra
    0.07
     Population
    0.07
    Small
    0.07
     commuting
    0.07
     Internal
    0.07
     decomposition
    0.07
    Act Density 0.002%

    No Known Activations