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

    Neuronpedia

    INDEX
    Explanations

    serial code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sö
    -0.07
    -second
    -0.07
    -0.07
     Kon
    -0.06
    early
    -0.06
    olta
    -0.06
     Jury
    -0.06
     ary
    -0.06
    _Con
    -0.06
    وية
    -0.06
    POSITIVE LOGITS
    !");↵
    0.07
    γγελ
    0.06
    =pk
    0.06
    .cmb
    0.06
     redistribute
    0.06
    Drink
    0.06
     });↵
    0.06
     будто
    0.06
    	rv
    0.06
    Aggregate
    0.06
    Act Density 0.001%

    No Known Activations