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

    Neuronpedia

    INDEX
    Explanations

    bed and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뿔
    0.93
    कर्ता
    0.93
    Bis
    0.90
    รส
    0.88
     derogatory
    0.88
     stub
    0.85
     winds
    0.85
     কব
    0.83
     mileage
    0.82
     bis
    0.82
    POSITIVE LOGITS
    ouin
    1.51
    chamber
    1.38
    clothes
    1.33
    ding
    1.27
    rijf
    1.21
    azz
    1.19
    フォード
    1.16
    rijven
    1.14
    annt
    1.13
    stead
    1.12
    Act Density 0.049%

    No Known Activations