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

    Neuronpedia

    INDEX
    Explanations

    Air Zoom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urses
    -0.08
    _pic
    -0.07
    ⟪
    -0.07
    糜
    -0.07
    wyn
    -0.07
     granted
    -0.06
    MIT
    -0.06
    entric
    -0.06
     qty
    -0.06
    ไพ
    -0.06
    POSITIVE LOGITS
    🌿
    0.07
    趟
    0.07
     المستوى
    0.06
     rom
    0.06
    (constants
    0.06
    ungalow
    0.06
    (schema
    0.06
     aby
    0.06
     einen
    0.06
     Rivers
    0.06
    Act Density 0.004%

    No Known Activations