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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     possibilities
    -0.07
    _contract
    -0.07
     بعد
    -0.07
    оля
    -0.07
    _area
    -0.07
    誤
    -0.07
    Jur
    -0.06
    .views
    -0.06
    .resp
    -0.06
    requent
    -0.06
    POSITIVE LOGITS
     goalie
    0.07
    	left
    0.06
    cci
    0.06
     Mitch
    0.06
    に見
    0.06
    JECTED
    0.06
     Mädchen
    0.06
    .mkdirs
    0.06
    localObject
    0.06
     Araştır
    0.06
    Act Density 0.002%

    No Known Activations