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

    Neuronpedia

    INDEX
    Explanations

    ith

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แรม
    -0.07
    (outfile
    -0.07
    .uc
    -0.06
    Netflix
    -0.06
    	q
    -0.06
     Singapore
    -0.06
    -plugin
    -0.06
     бра
    -0.06
    Los
    -0.06
     Ryder
    -0.06
    POSITIVE LOGITS
    ัตน
    0.08
    	glVertex
    0.07
     dopl
    0.07
     สถาน
    0.07
    ěst
    0.06
    ัปดาห
    0.06
     논
    0.06
     widen
    0.06
    ndef
    0.06
     syll
    0.06
    Act Density 0.003%

    No Known Activations