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

    Neuronpedia

    INDEX
    Explanations

    Chinese products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    363
    -0.06
    276
    -0.06
     Smoke
    -0.06
    286
    -0.06
     spelled
    -0.06
    _CLEAN
    -0.06
    373
    -0.06
    367
    -0.06
    381
    -0.06
     Bend
    -0.06
    POSITIVE LOGITS
     muss
    0.07
    стра
    0.06
     З
    0.06
    ISTICS
    0.06
    avity
    0.06
    вания
    0.06
     Glock
    0.06
    ализи
    0.06
    iating
    0.06
     Murdoch
    0.06
    Act Density 0.185%

    No Known Activations