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

    Neuronpedia

    INDEX
    Explanations

    compositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     underwent
    -0.07
    載
    -0.07
    wife
    -0.07
     Eigen
    -0.07
    ץ
    -0.07
     Дан
    -0.07
     Gson
    -0.07
    搬家
    -0.07
     llen
    -0.06
    Close
    -0.06
    POSITIVE LOGITS
    (media
    0.08
     Pitch
    0.08
    减免
    0.07
     ожида
    0.07
    ADI
    0.07
     terminator
    0.07
    insi
    0.07
     mentality
    0.07
     shocking
    0.07
    න
    0.07
    Act Density 0.009%

    No Known Activations