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

    Neuronpedia

    INDEX
    Explanations

    33

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reinterpret
    -0.06
     Kraj
    -0.06
     �
    -0.06
     ph
    -0.06
     Trudeau
    -0.06
     org
    -0.06
    aku
    -0.06
    -0.06
     tf
    -0.06
    _hits
    -0.06
    POSITIVE LOGITS
     lowercase
    0.08
    继续
    0.07
    dateFormat
    0.07
     quality
    0.07
    .dispose
    0.06
     TERMS
    0.06
    撮
    0.06
    文件
    0.06
     Quality
    0.06
    ी↵
    0.06
    Act Density 0.067%

    No Known Activations