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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мощ
    -0.07
     προς
    -0.07
    postData
    -0.06
     usefulness
    -0.06
     дли
    -0.06
     vast
    -0.06
     openness
    -0.06
     применя
    -0.06
    ो
    -0.06
     la
    -0.06
    POSITIVE LOGITS
    _MUX
    0.07
    resse
    0.06
     Riding
    0.06
     Igor
    0.06
     whale
    0.06
     Cached
    0.06
     Rover
    0.06
    →→
    0.06
    arlo
    0.06
     eBooks
    0.06
    Act Density 0.011%

    No Known Activations