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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _hw
    -0.08
     tục
    -0.07
     Gaussian
    -0.07
     Helpers
    -0.06
    oplan
    -0.06
    _threads
    -0.06
    anya
    -0.06
     Illum
    -0.06
    iv
    -0.06
    oled
    -0.06
    POSITIVE LOGITS
     <>↵
    0.06
    �p
    0.06
    Louis
    0.06
    "f
    0.06
     ACTIVE
    0.06
    MouseDown
    0.06
    roupon
    0.06
    ='')↵
    0.06
    ;'
    0.06
    "`
    0.06
    Act Density 0.185%

    No Known Activations