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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pk
    -0.07
     coverage
    -0.07
     อำ
    -0.06
    ApiOperation
    -0.06
    .Sync
    -0.06
     су
    -0.06
     head
    -0.06
     jinak
    -0.06
     Water
    -0.06
     parental
    -0.06
    POSITIVE LOGITS
    ционного
    0.06
     ").
    0.06
    ![
    0.06
    abile
    0.06
    .repositories
    0.06
    ров
    0.06
    着
    0.06
    pane
    0.06
    rotein
    0.06
     этих
    0.06
    Act Density 0.020%

    No Known Activations