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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    东西
    -0.07
     ministers
    -0.07
     difíc
    -0.07
    虑
    -0.07
    �
    -0.07
    bert
    -0.07
     laying
    -0.06
    horse
    -0.06
     Romance
    -0.06
    esch
    -0.06
    POSITIVE LOGITS
     resolving
    0.07
    ENTION
    0.06
     температу
    0.06
    []>(
    0.06
    @Spring
    0.06
    (tv
    0.06
    (expect
    0.06
    >Please
    0.06
    _AHB
    0.06
     Expert
    0.05
    Act Density 0.035%

    No Known Activations