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

    Neuronpedia

    INDEX
    Explanations

    Billions of dollars

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عليك
    -0.08
     thr
    -0.07
    ほう
    -0.07
    齁
    -0.07
     DELETE
    -0.07
    请假
    -0.07
     skip
    -0.07
    靿
    -0.07
    drawer
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    乌鲁木
    0.08
    onia
    0.07
    鹚
    0.07
    ₯
    0.07
    天津
    0.07
     UNIVERS
    0.07
    نتج
    0.07
     variety
    0.07
    ERA
    0.07
    gren
    0.07
    Act Density 0.042%

    No Known Activations