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

    Neuronpedia

    INDEX
    Explanations

    depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ность
    1.09
     Uhr
    1.05
    جه
    1.02
    ности
    0.98
    ランス
    0.94
    nement
    0.92
    schluss
    0.91
     fazer
    0.89
    အား
    0.89
    عة
    0.89
    POSITIVE LOGITS
    𝐓
    1.29
     pests
    1.28
    MESH
    1.27
    ac
    1.24
    CYCL
    1.22
     Zacks
    1.21
     Veterans
    1.20
     weaves
    1.19
    unico
    1.18
    mesh
    1.18
    Act Density 0.001%

    No Known Activations