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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smallest
    -0.08
    才会
    -0.08
    worked
    -0.07
    views
    -0.07
     richer
    -0.07
     require
    -0.07
    深处
    -0.07
    .show
    -0.07
    _point
    -0.07
    合资
    -0.07
    POSITIVE LOGITS
    뮬
    0.08
     следует
    0.08
    Carthy
    0.07
     контр
    0.07
     absorbing
    0.07
     narr
    0.07
    熻
    0.07
     niekt
    0.06
    맘
    0.06
     Tennessee
    0.06
    Act Density 0.047%

    No Known Activations