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

    Neuronpedia

    INDEX
    Explanations

    past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staged
    -0.07
    _();↵
    -0.07
    宽
    -0.07
     Metric
    -0.07
     Marker
    -0.06
    orsche
    -0.06
     slew
    -0.06
     テ
    -0.06
     Alec
    -0.06
     Delay
    -0.06
    POSITIVE LOGITS
     specifically
    0.06
    /local
    0.06
     renters
    0.06
     eruption
    0.06
    .....
    0.06
    iciar
    0.06
     inertia
    0.06
    AVAILABLE
    0.05
    Queue
    0.05
     distress
    0.05
    Act Density 0.007%

    No Known Activations