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

    Neuronpedia

    INDEX
    Explanations

    ivariate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    moth
    -0.09
    .getM
    -0.08
    VB
    -0.07
    comput
    -0.07
    ví
    -0.07
    wyn
    -0.07
     ctypes
    -0.07
    orsch
    -0.06
    	fprintf
    -0.06
    neh
    -0.06
    POSITIVE LOGITS
     reste
    0.07
     veniam
    0.07
    第
    0.07
     shelters
    0.07
    (first
    0.06
    又一次
    0.06
    这里是
    0.06
     llegar
    0.06
     reorder
    0.06
    licative
    0.06
    Act Density 0.003%

    No Known Activations