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

    Neuronpedia

    INDEX
    Explanations

    generalization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trab
    -0.07
     byte
    -0.07
     Hub
    -0.06
     Blackhawks
    -0.06
     chore
    -0.06
     collaborations
    -0.06
     BTC
    -0.06
    \r
    -0.06
    \u
    -0.06
     servicing
    -0.06
    POSITIVE LOGITS
     generalized
    0.07
    未
    0.07
    입
    0.07
    сті
    0.07
    veys
    0.06
    ogie
    0.06
    sole
    0.06
     generalize
    0.06
    cs
    0.06
    ισμού
    0.06
    Act Density 0.009%

    No Known Activations