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

    Neuronpedia

    INDEX
    Explanations

    legal case citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Uu
    -0.81
    terr
    -0.81
    umd
    -0.76
     Presents
    -0.73
    Toll
    -0.73
    了一个
    -0.72
    rower
    -0.71
    了她
    -0.70
    になると
    -0.70
    qy
    -0.69
    POSITIVE LOGITS
    Pflege
    0.92
     infrastructures
    0.91
    Lalu
    0.86
     Nvidia
    0.84
    詩
    0.84
     délib
    0.83
    licit
    0.82
    щал
    0.82
     afir
    0.82
    Bukan
    0.82
    Act Density 0.145%

    No Known Activations