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

    Neuronpedia

    INDEX
    Explanations

    defendant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zenie
    -0.07
    きた
    -0.07
    𬶠
    -0.07
    细节
    -0.07
    ישי
    -0.07
    칠
    -0.07
    끈
    -0.07
    ились
    -0.06
     Rig
    -0.06
    测试
    -0.06
    POSITIVE LOGITS
     נע
    0.07
    _supported
    0.07
    processors
    0.07
     bây
    0.06
    三方
    0.06
     succession
    0.06
    鲍
    0.06
    �
    0.06
    readOnly
    0.06
    风情
    0.06
    Act Density 0.015%

    No Known Activations