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

    Neuronpedia

    INDEX
    Explanations

    coherent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     requestOptions
    -0.08
     August
    -0.08
    衽
    -0.08
    江西
    -0.07
    نطق
    -0.07
    (coord
    -0.07
     splits
    -0.07
    Fourth
    -0.07
    בוע
    -0.07
     bull
    -0.07
    POSITIVE LOGITS
     (;
    0.07
    橱柜
    0.07
    sequence
    0.07
     ])
    0.06
    ?;↵↵
    0.06
    掃
    0.06
     コ
    0.06
     sources
    0.06
    uity
    0.06
    ﯱ
    0.06
    Act Density 0.006%

    No Known Activations