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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quickly
    -0.07
    цы
    -0.07
    quire
    -0.06
     dalle
    -0.06
     immediately
    -0.06
    دار
    -0.06
     distributing
    -0.06
     dicks
    -0.06
     search
    -0.06
    _events
    -0.06
    POSITIVE LOGITS
    visor
    0.06
    .req
    0.06
    (END
    0.06
     '~/
    0.06
     cup
    0.06
     SUV
    0.06
    _fail
    0.06
     万元
    0.06
     Cup
    0.06
     الصن
    0.06
    Act Density 0.029%

    No Known Activations