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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Log
    -0.08
     Close
    -0.07
    ӎ
    -0.07
    胩
    -0.07
    世界上最
    -0.07
     passes
    -0.07
    Return
    -0.07
    ⾛
    -0.07
    _walk
    -0.07
    各省
    -0.07
    POSITIVE LOGITS
     şi
    0.07
    strike
    0.07
    (Gravity
    0.07
    骎
    0.07
     ups
    0.07
     ди
    0.07
     goog
    0.06
    оф
    0.06
    忉
    0.06
    ༼
    0.06
    Act Density 0.045%

    No Known Activations