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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     차
    -0.07
     Explore
    -0.07
     dancing
    -0.06
     Bucket
    -0.06
     spit
    -0.06
    915
    -0.06
     Byrne
    -0.06
     朝
    -0.06
    _any
    -0.06
     industri
    -0.06
    POSITIVE LOGITS
    rud
    0.07
    Hum
    0.06
     newPos
    0.06
    ))==
    0.06
     ahead
    0.06
    шись
    0.06
    "]))↵
    0.06
    ství
    0.06
    academic
    0.06
    uality
    0.06
    Act Density 0.022%

    No Known Activations