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

    Neuronpedia

    INDEX
    Explanations

    removed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chall
    -0.07
     AssemblyProduct
    -0.07
    광고
    -0.06
     찾
    -0.06
     Merc
    -0.06
    通り
    -0.06
    하면서
    -0.06
    TAB
    -0.06
     серд
    -0.06
    partial
    -0.06
    POSITIVE LOGITS
     mines
    0.07
    .Ui
    0.06
    .Many
    0.06
    ynamics
    0.06
     пораж
    0.06
    .in
    0.06
    (prev
    0.06
     fifty
    0.06
    ..'
    0.06
    22
    0.06
    Act Density 0.000%

    No Known Activations