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

    Neuronpedia

    INDEX
    Explanations

    Lacking good judgement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ingredients
    -0.07
    UIViewController
    -0.06
    -feature
    -0.06
     "\">
    -0.06
    Warehouse
    -0.06
     نت
    -0.06
    .Insert
    -0.06
    епти
    -0.06
     battleground
    -0.06
     desn
    -0.06
    POSITIVE LOGITS
    choice
    0.06
     øns
    0.06
    력
    0.06
     quản
    0.06
     filho
    0.06
    .Email
    0.06
     backward
    0.06
    營
    0.06
     توسعه
    0.06
    μος
    0.06
    Act Density 0.017%

    No Known Activations