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

    Neuronpedia

    INDEX
    Explanations

    diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    äden
    1.18
     ase
    1.05
     polvo
    1.03
     lewat
    1.02
    রাজনৈতিক
    1.02
     Neither
    1.02
     mètres
    1.02
    imismo
    1.01
     vértice
    0.98
     paar
    0.98
    POSITIVE LOGITS
    一个
    1.02
    יש
    0.98
    给定
    0.97
    das
    0.96
    ப
    0.96
    cast
    0.95
    館
    0.95
     tooltip
    0.94
     kidd
    0.91
    ক
    0.91
    Act Density 0.000%

    No Known Activations