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

    Neuronpedia

    INDEX
    Explanations

    cron jobs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Add
    -0.07
     Commod
    -0.06
     ComboBox
    -0.06
     wizard
    -0.06
     Independent
    -0.06
    全面
    -0.06
    健康
    -0.06
     november
    -0.06
     pseudo
    -0.06
     đàn
    -0.06
    POSITIVE LOGITS
    降雨
    0.07
    fcn
    0.07
    (entry
    0.07
    DBG
    0.07
     scraps
    0.07
     HOT
    0.07
    ❚
    0.07
    (DBG
    0.07
    ယ
    0.07
    şim
    0.07
    Act Density 0.144%

    No Known Activations