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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ruby
    -0.07
     {|
    -0.07
     emph
    -0.06
     iktidar
    -0.06
    ocha
    -0.06
     asserting
    -0.06
     defiant
    -0.06
    _sort
    -0.06
     trustees
    -0.06
     Coul
    -0.06
    POSITIVE LOGITS
    reply
    0.07
    знач
    0.07
    (bbox
    0.06
    Bitcoin
    0.06
     emissions
    0.06
    υνα
    0.06
     ff
    0.06
    .so
    0.06
    .Font
    0.06
    	common
    0.06
    Act Density 0.000%

    No Known Activations