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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ζό
    -0.06
     bý
    -0.06
    .Un
    -0.06
    gebn
    -0.06
     youngest
    -0.06
     DbSet
    -0.06
     Using
    -0.06
    Their
    -0.06
     Tooth
    -0.06
     flush
    -0.06
    POSITIVE LOGITS
    重大
    0.08
    uspended
    0.07
    _energy
    0.07
     News
    0.06
     Kits
    0.06
    .RES
    0.06
     contentView
    0.06
    _BEGIN
    0.06
    .chapter
    0.06
     타
    0.06
    Act Density 0.130%

    No Known Activations