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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xr
    -0.07
     ihre
    -0.07
     Verse
    -0.07
    EMPLATE
    -0.07
    总裁
    -0.07
     içerisinde
    -0.07
    占地面积
    -0.07
    kerja
    -0.07
    Xd
    -0.07
    ruptcy
    -0.07
    POSITIVE LOGITS
     increasing
    0.07
    PACK
    0.07
    计提
    0.07
     Ni
    0.07
    উ
    0.07
    ：↵
    0.07
    occus
    0.07
    peats
    0.07
    Adjust
    0.07
     apply
    0.06
    Act Density 0.025%

    No Known Activations