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

    Neuronpedia

    INDEX
    Explanations

    axioms and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conteú
    0.54
    Toyota
    0.50
     которого
    0.46
    atthakath
    0.46
    વેશ
    0.45
    屬於
    0.45
     necessária
    0.44
    铷
    0.44
     configura
    0.44
    ➔
    0.44
    POSITIVE LOGITS
     people
    0.48
     mountains
    0.47
     KL
    0.46
     मैं
    0.44
     comparing
    0.44
    我很
    0.43
     (
    0.43
     Mountain
    0.43
     mountain
    0.42
     lovers
    0.42
    Act Density 0.006%

    No Known Activations