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

    Neuronpedia

    INDEX
    Explanations

    does

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SAFE
    -0.07
    _Sub
    -0.07
     ignorance
    -0.07
     infect
    -0.07
    .Printf
    -0.06
     здесь
    -0.06
    ним
    -0.06
     paradigm
    -0.06
    	for
    -0.06
    Patch
    -0.06
    POSITIVE LOGITS
    fillType
    0.06
    .sulake
    0.06
    피
    0.06
     Hotels
    0.06
    (img
    0.06
     آمار
    0.06
     g
    0.06
     Xu
    0.06
    (pe
    0.06
     Friedrich
    0.06
    Act Density 0.000%

    No Known Activations