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

    Neuronpedia

    INDEX
    Explanations

    encoded strings or URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ట
    0.50
    important
    0.48
    antal
    0.48
     TK
    0.48
     irritability
    0.46
     Moor
    0.46
     Important
    0.45
     اہم
    0.45
    ँच
    0.45
     Jug
    0.45
    POSITIVE LOGITS
    తుందని
    0.48
    ará
    0.47
     catégorie
    0.46
    وال
    0.46
    gehen
    0.45
     docks
    0.45
     prendere
    0.44
     informieren
    0.44
     parts
    0.43
     যায়
    0.43
    Act Density 0.018%

    No Known Activations