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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Teacher
    -0.07
     vox
    -0.06
    ाद
    -0.06
    ptr
    -0.06
    asures
    -0.06
    enty
    -0.06
    ENDER
    -0.06
     Favorite
    -0.06
     büyük
    -0.06
    ourt
    -0.06
    POSITIVE LOGITS
    (crate
    0.07
     tren
    0.07
    TexCoord
    0.07
     gastro
    0.06
    dn
    0.06
     traj
    0.06
    하며
    0.06
    .Ο
    0.06
    BorderColor
    0.06
    ]&
    0.06
    Act Density 0.012%

    No Known Activations