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

    Neuronpedia

    INDEX
    Explanations

    step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erweise
    1.37
     Tiếp
    1.24
    Ре
    1.22
     disturbances
    1.19
    theless
    1.18
     completos
    1.18
     Truy
    1.16
     Purchases
    1.16
     coalgebras
    1.15
    рик
    1.13
    POSITIVE LOGITS
    म
    1.43
    ش
    1.20
    is
    1.17
    什麼
    1.13
    ge
    1.07
    言う
    1.06
    ian
    1.03
    Cómo
    1.03
    ടന
    1.02
    erebbe
    1.02
    Act Density 0.001%

    No Known Activations