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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    numbers
    -0.08
    大会
    -0.08
    Regards
    -0.07
     Centers
    -0.07
    !?
    -0.06
    Graphic
    -0.06
    Safety
    -0.06
    	events
    -0.06
     dương
    -0.06
    StackTrace
    -0.06
    POSITIVE LOGITS
    ESPN
    0.06
     دانلود
    0.06
     Creed
    0.06
    期
    0.06
     Jungle
    0.06
     RET
    0.06
     Nikki
    0.06
    _episode
    0.06
     İstanbul
    0.06
    ;&#
    0.06
    Act Density 0.026%

    No Known Activations