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

    Neuronpedia

    INDEX
    Explanations

    Solitude, Adapter Layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মি
    1.06
     solids
    0.97
     WaitFor
    0.94
     commenced
    0.93
    வான்
    0.91
     simplicial
    0.90
     duplicates
    0.89
     nominally
    0.89
     threats
    0.88
     сент
    0.88
    POSITIVE LOGITS
    ỗ
    1.06
    Und
    1.03
    ྔ
    1.01
    oción
    0.97
    喚
    0.97
    หา
    0.97
     ব্যক্তিদের
    0.96
    accharides
    0.96
    ið
    0.96
    CNN
    0.95
    Act Density 0.020%

    No Known Activations