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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cape
    -0.08
     fantastic
    -0.07
    Nevertheless
    -0.07
    Classic
    -0.07
     RTC
    -0.07
    Thanks
    -0.07
    Ross
    -0.07
    طق
    -0.07
     Repeat
    -0.07
     fighter
    -0.07
    POSITIVE LOGITS
     �
    0.07
    妪
    0.07
    垒
    0.07
    是最好的
    0.07
    优点
    0.07
     constructs
    0.07
    "
    0.07
    瓴
    0.07
    班组
    0.07
    h
    0.07
    Act Density 0.014%

    No Known Activations