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

    Neuronpedia

    INDEX
    Explanations

    future plans/events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edes
    -0.08
     dever
    -0.07
     Wooden
    -0.07
    enced
    -0.07
    _begin
    -0.07
    _ub
    -0.07
     fusion
    -0.06
    ına
    -0.06
     observers
    -0.06
     roll
    -0.06
    POSITIVE LOGITS
    _NON
    0.07
     розта
    0.06
     prostřednictvím
    0.06
     merkez
    0.06
     khẳng
    0.06
    ffect
    0.06
     facial
    0.06
    运
    0.06
    632
    0.06
    ประส
    0.06
    Act Density 0.020%

    No Known Activations