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

    Neuronpedia

    INDEX
    Explanations

    react

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mAh
    -0.06
     спис
    -0.06
     nerd
    -0.06
     meget
    -0.06
     会
    -0.06
     Recorder
    -0.06
     πλα
    -0.06
    icaret
    -0.06
     pods
    -0.06
     desires
    -0.06
    POSITIVE LOGITS
     describing
    0.06
     caused
    0.06
    uddenly
    0.06
     분석
    0.06
    963
    0.06
     عوامل
    0.06
    жди
    0.06
    astics
    0.06
     Opposition
    0.06
    empor
    0.06
    Act Density 0.011%

    No Known Activations